messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click on the blue spot to access the \"eBay shopping\" tab which likely contains the shopping cart. Then, check if you can find \"Acer Nitro\" in the available products. After locating it, click to add it to your shopping cart by tapping the PLUS button. Finally, select checkout to complete your purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [46, 83]}<image>Thought: Type \"costco\" in the search bar to find the website. Click on the appropriate link for Costco to navigate to the site. From there, locate and add \"acer nitro\" to the shopping cart. Finally, select the checkout option to proceed with the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 364]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Costco to access the shopping website for your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 399]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_2.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_3.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_4.png"
] | 6,400
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Type \"costco\" in the search bar to find the website. Click on the appropriate link for Costco to navigate to the site. From there, locate and add \"acer nitro\" to the shopping cart. Finally, select the checkout option to proceed with the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 364]}<image>Thought: Click on Costco to access the shopping website for your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 399]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Costco Wholesale\" link to access the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 694]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_3.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_4.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_5.png"
] | 6,401
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click on Costco to access the shopping website for your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 399]}<image>Thought: Click on the \"Costco Wholesale\" link to access the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 694]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to begin looking for the \"acer nitro\" product in Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 228]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_4.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_5.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_6.png"
] | 6,402
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click on the \"Costco Wholesale\" link to access the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 694]}<image>Thought: Click on the search bar to begin looking for the \"acer nitro\" product in Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 228]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer nitro\" in the search bar to find the product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_5.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_6.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_7.png"
] | 6,403
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click on the search bar to begin looking for the \"acer nitro\" product in Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 228]}<image>Thought: Type \"acer nitro\" in the search bar to find the product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Acer Nitro 32\" option in the search results to select it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 573]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_6.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_7.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_8.png"
] | 6,404
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Type \"acer nitro\" in the search bar to find the product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>Thought: Click on the \"Acer Nitro 32\" option in the search results to select it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 573]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional details about the Acer Nitro monitor on Costco's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_7.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_8.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_9.png"
] | 6,405
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click on the \"Acer Nitro 32\" option in the search results to select it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 573]}<image>Thought: Scroll down to view additional details about the Acer Nitro monitor on Costco's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the pricing and delivery options for the Acer Nitro monitor.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_8.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_9.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_10.png"
] | 6,406
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Scroll down to view additional details about the Acer Nitro monitor on Costco's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the pricing and delivery options for the Acer Nitro monitor.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to place the \"acer nitro\" in the shopping cart for checkout later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 660]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_9.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_10.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_11.png"
] | 6,407
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Scroll down to view the pricing and delivery options for the Acer Nitro monitor.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to place the \"acer nitro\" in the shopping cart for checkout later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 660]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View Cart\" to review the items in your Costco shopping cart and proceed to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 491]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_10.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_11.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_12.png"
] | 6,408
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click \"Add to Cart\" to place the \"acer nitro\" in the shopping cart for checkout later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 660]}<image>Thought: Click \"View Cart\" to review the items in your Costco shopping cart and proceed to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 491]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Checkout button to proceed with purchasing the Acer Nitro monitor from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [314, 1052]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_11.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_12.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_13.png"
] | 6,409
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco. Add \"acer nitro\" to the cart on costco, then select checkout.<image>Thought: Click \"View Cart\" to review the items in your Costco shopping cart and proceed to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 491]}<image>Thought: Click the Checkout button to proceed with purchasing the Acer Nitro monitor from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [314, 1052]}<image>",
"role": "user"
},
{
"content": "Thought: Status task complete indicates that the user has successfully completed their intended operations on the Costco shopping cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9743213714586592477_12.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_13.png",
"training_data/AITW/aitw_images/webshopping/9743213714586592477_14.png"
] | 6,410
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the Google Photos app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_0.png"
] | 6,411
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: Press home to exit the Google Photos app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the CHAT icon to access assistance for viewing the shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 536]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_0.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_1.png"
] | 6,412
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: Press home to exit the Google Photos app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the CHAT icon to access assistance for viewing the shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 536]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bestbuy\" in the search bar to quickly find the shopping site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_0.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_1.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_2.png"
] | 6,413
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: Click on the CHAT icon to access assistance for viewing the shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 536]}<image>Thought: Type \"bestbuy\" in the search bar to quickly find the shopping site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Best\" to access the Best Buy website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 78]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_1.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_2.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_3.png"
] | 6,414
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: Type \"bestbuy\" in the search bar to quickly find the shopping site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>Thought: Click on \"Best\" to access the Best Buy website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 78]}<image>",
"role": "user"
},
{
"content": "Thought: The user clicked on Amazon because they mistakenly selected the sponsored link instead of finding Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 269]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_2.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_3.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_4.png"
] | 6,415
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: Click on \"Best\" to access the Best Buy website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 78]}<image>Thought: The user clicked on Amazon because they mistakenly selected the sponsored link instead of finding Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 269]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access the cart after searching for best buys.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [252, 69]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_3.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_4.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_5.png"
] | 6,416
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.<image>Thought: The user clicked on Amazon because they mistakenly selected the sponsored link instead of finding Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 269]}<image>Thought: Click SHOPPING CART to access the cart after searching for best buys.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [252, 69]}<image>",
"role": "user"
},
{
"content": "Thought: status task impossible; you cannot view the shopping cart on Best Buy as you are on Amazon's cart page.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6808501972571595320_4.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_5.png",
"training_data/AITW/aitw_images/webshopping/6808501972571595320_6.png"
] | 6,417
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome icon to open a web browser for shopping on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 914]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_0.png"
] | 6,418
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>Thought: Click the Google Chrome icon to open a web browser for shopping on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 914]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible indicates that the user cannot complete their intended operation as they are on the wrong website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 75]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_0.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_1.png"
] | 6,419
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>Thought: Click the Google Chrome icon to open a web browser for shopping on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 914]}<image>Thought: Status task impossible indicates that the user cannot complete their intended operation as they are on the wrong website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 75]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Walmart.com link to access the shopping site. After loading the site, navigate to add Logitech G Pro to your cart. Then, locate and select the checkout option to finalize your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 415]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_0.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_1.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_2.png"
] | 6,420
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>Thought: Status task impossible indicates that the user cannot complete their intended operation as they are on the wrong website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 75]}<image>Thought: Click the Walmart.com link to access the shopping site. After loading the site, navigate to add Logitech G Pro to your cart. Then, locate and select the checkout option to finalize your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 415]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the $109.99 price to see the details of the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 146]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_1.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_2.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_3.png"
] | 6,421
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>Thought: Click the Walmart.com link to access the shopping site. After loading the site, navigate to add Logitech G Pro to your cart. Then, locate and select the checkout option to finalize your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 415]}<image>Thought: Click on the $109.99 price to see the details of the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 146]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue to checkout\" to proceed with the order after adding the Logitech G Pro to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [183, 999]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_2.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_3.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_4.png"
] | 6,422
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add logitech g pro to the cart on walmart.com, then select checkout.<image>Thought: Click on the $109.99 price to see the details of the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 146]}<image>Thought: Click \"Continue to checkout\" to proceed with the order after adding the Logitech G Pro to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [183, 999]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully accessed the cart to see your items, confirming completion of the task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15738010032189863807_3.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_4.png",
"training_data/AITW/aitw_images/webshopping/15738010032189863807_5.png"
] | 6,423
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to access the email app and check if there are any confirmations or updates from Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 925]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_0.png"
] | 6,424
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the ENVELOPE to access the email app and check if there are any confirmations or updates from Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 925]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to open it and type the product you need. You aim to find \"beats solo 3\". After typing, press enter to perform the search. This operation is necessary to navigate back to Best Buy or find relevant information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [313, 60]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_0.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_1.png"
] | 6,425
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the ENVELOPE to access the email app and check if there are any confirmations or updates from Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 925]}<image>Thought: Click the search bar to open it and type the product you need. You aim to find \"beats solo 3\". After typing, press enter to perform the search. This operation is necessary to navigate back to Best Buy or find relevant information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [313, 60]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Best Buy\" link to navigate to the official store and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 367]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_0.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_1.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_2.png"
] | 6,426
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the search bar to open it and type the product you need. You aim to find \"beats solo 3\". After typing, press enter to perform the search. This operation is necessary to navigate back to Best Buy or find relevant information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [313, 60]}<image>Thought: Click on the \"Best Buy\" link to navigate to the official store and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 367]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to view the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 185]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_1.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_2.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_3.png"
] | 6,427
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click on the \"Best Buy\" link to navigate to the official store and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 367]}<image>Thought: Click the SHOPPING CART icon to view the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 185]}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to start clearing items from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 853]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_2.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_3.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_4.png"
] | 6,428
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the SHOPPING CART icon to view the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 185]}<image>Thought: Click Remove to start clearing items from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 853]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the cart icon to access the current items in your cart. Since the GUI shows \"Your cart is empty,\" there are no items to clear. You need to return to the main page and search for \"beats solo 3.\" After finding it, click \"Add to Cart\" to include it in your shopping cart. Finally, select checkout to proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 166]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_3.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_4.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_5.png"
] | 6,429
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click Remove to start clearing items from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 853]}<image>Thought: Click on the cart icon to access the current items in your cart. Since the GUI shows \"Your cart is empty,\" there are no items to clear. You need to return to the main page and search for \"beats solo 3.\" After finding it, click \"Add to Cart\" to include it in your shopping cart. Finally, select checkout to proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 166]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"beats solo 3\" in the search bar to find the desired item for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"beats solo 3\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_4.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_5.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_6.png"
] | 6,430
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click on the cart icon to access the current items in your cart. Since the GUI shows \"Your cart is empty,\" there are no items to clear. You need to return to the main page and search for \"beats solo 3.\" After finding it, click \"Add to Cart\" to include it in your shopping cart. Finally, select checkout to proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 166]}<image>Thought: Type \"beats solo 3\" in the search bar to find the desired item for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"beats solo 3\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"beats solo 3.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 124]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_5.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_6.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_7.png"
] | 6,431
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Type \"beats solo 3\" in the search bar to find the desired item for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"beats solo 3\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"beats solo 3.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 124]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the desired item \"beats solo 3\" in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 960]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_6.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_7.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_8.png"
] | 6,432
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the magnifying glass to initiate a search for \"beats solo 3.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 124]}<image>Thought: Click \"Add to Cart\" to include the desired item \"beats solo 3\" in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 960]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include \"beats solo 3\" in your shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 985]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_7.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_8.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_9.png"
] | 6,433
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click \"Add to Cart\" to include the desired item \"beats solo 3\" in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 960]}<image>Thought: Click the \"Add to Cart\" button to include \"beats solo 3\" in your shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 985]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Go to cart\" to view and manage the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 116]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_8.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_9.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_10.png"
] | 6,434
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click the \"Add to Cart\" button to include \"beats solo 3\" in your shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 985]}<image>Thought: Click \"Go to cart\" to view and manage the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 116]}<image>",
"role": "user"
},
{
"content": "Thought: Clicking Checkout initiates the purchasing process after adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [238, 625]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_9.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_10.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_11.png"
] | 6,435
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add \"beats solo 3\" to the cart on bestbuy, then select checkout.<image>Thought: Click \"Go to cart\" to view and manage the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 116]}<image>Thought: Clicking Checkout initiates the purchasing process after adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [238, 625]}<image>",
"role": "user"
},
{
"content": "Thought: The task is now complete, indicating that the user successfully cleared the cart, added \"beats solo 3\", and checked out on Best Buy.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2764782070473941885_10.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_11.png",
"training_data/AITW/aitw_images/webshopping/2764782070473941885_12.png"
] | 6,436
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current application due to an unexpected error preventing further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_0.png"
] | 6,437
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to exit the current application due to an unexpected error preventing further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the ENVELOPE icon to open the email app and check for notifications or verification.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 466]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_0.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_1.png"
] | 6,438
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to exit the current application due to an unexpected error preventing further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the ENVELOPE icon to open the email app and check for notifications or verification.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 466]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"stco.com\" to navigate to the desired website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [196, 85]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_0.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_1.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_2.png"
] | 6,439
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the ENVELOPE icon to open the email app and check for notifications or verification.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 466]}<image>Thought: Click on \"stco.com\" to navigate to the desired website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [196, 85]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_1.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_2.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_3.png"
] | 6,440
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"stco.com\" to navigate to the desired website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [196, 85]}<image>Thought: Type \"ebay\" in the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on eBay to open the website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 277]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_2.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_3.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_4.png"
] | 6,441
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"ebay\" in the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>Thought: Click on eBay to open the website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 277]}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to navigate directly to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [169, 537]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_3.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_4.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_5.png"
] | 6,442
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on eBay to open the website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 277]}<image>Thought: Click the eBay link to navigate directly to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [169, 537]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for a\" to begin inputting my search query for the bose soundlink product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 244]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_4.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_5.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_6.png"
] | 6,443
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the eBay link to navigate directly to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [169, 537]}<image>Thought: Click on \"Search for a\" to begin inputting my search query for the bose soundlink product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 244]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bose soundlink\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_5.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_6.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_7.png"
] | 6,444
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Search for a\" to begin inputting my search query for the bose soundlink product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 244]}<image>Thought: Type \"bose soundlink\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"bose soundlink flex\" to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 310]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_6.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_7.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_8.png"
] | 6,445
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"bose soundlink\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>Thought: Click on \"bose soundlink flex\" to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 310]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for the \"bose soundlink\" query on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_7.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_8.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_9.png"
] | 6,446
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"bose soundlink flex\" to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 310]}<image>Thought: Scroll down to view more search results for the \"bose soundlink\" query on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Bose\" entry to view product details and proceed with the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 329]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_8.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_9.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_10.png"
] | 6,447
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay.com. Search for bose soundlink on ebay.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more search results for the \"bose soundlink\" query on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"Bose\" entry to view product details and proceed with the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 329]}<image>",
"role": "user"
},
{
"content": "Thought: The task cannot be completed due to a redirect error on the eBay website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8478424100400311060_9.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_10.png",
"training_data/AITW/aitw_images/webshopping/8478424100400311060_11.png"
] | 6,448
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible since the user is on Best Buy's sign-in page, not Amazon.com to clear the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 105]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_0.png"
] | 6,449
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Status task impossible since the user is on Best Buy's sign-in page, not Amazon.com to clear the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 105]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" in the web address bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_0.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_1.png"
] | 6,450
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Status task impossible since the user is on Best Buy's sign-in page, not Amazon.com to clear the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 105]}<image>Thought: Type \"amazon.com\" in the web address bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon.com to access the website needed for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_0.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_1.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_2.png"
] | 6,451
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type \"amazon.com\" in the web address bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Click on Amazon.com to access the website needed for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 184]}<image>",
"role": "user"
},
{
"content": "Thought: You need to type the characters displayed in the image to proceed with your shopping on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 778]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_1.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_2.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_3.png"
] | 6,452
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click on Amazon.com to access the website needed for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 184]}<image>Thought: You need to type the characters displayed in the image to proceed with your shopping on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 778]}<image>",
"role": "user"
},
{
"content": "Thought: Type the characters from the captcha to prove I am not a robot on the amazon.com GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"PAMTBA\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_2.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_3.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_4.png"
] | 6,453
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: You need to type the characters displayed in the image to proceed with your shopping on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 778]}<image>Thought: Type the characters from the captcha to prove I am not a robot on the amazon.com GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"PAMTBA\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue shopping\" to bypass the CAPTCHA and proceed with searching for the Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 923]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_3.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_4.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_5.png"
] | 6,454
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type the characters from the captcha to prove I am not a robot on the amazon.com GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"PAMTBA\", \"position\": null}<image>Thought: Click \"Continue shopping\" to bypass the CAPTCHA and proceed with searching for the Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 923]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue shopping\" to bypass the captcha and return to browsing on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 920]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_4.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_5.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_6.png"
] | 6,455
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click \"Continue shopping\" to bypass the CAPTCHA and proceed with searching for the Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 923]}<image>Thought: Click \"Continue shopping\" to bypass the captcha and return to browsing on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 920]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to view current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 174]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_5.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_6.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_7.png"
] | 6,456
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click \"Continue shopping\" to bypass the captcha and return to browsing on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 920]}<image>Thought: Click the SHOPPING CART to view current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 174]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin searching for \"logitech g903\" on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [324, 246]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_6.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_7.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_8.png"
] | 6,457
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART to view current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 174]}<image>Thought: Click the search bar to begin searching for \"logitech g903\" on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [324, 246]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g903\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_7.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_8.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_9.png"
] | 6,458
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the search bar to begin searching for \"logitech g903\" on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [324, 246]}<image>Thought: Type \"logitech g903\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"g903\" to select the first entry from the search results displayed in the suggestion box.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [152, 314]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_8.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_9.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_10.png"
] | 6,459
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type \"logitech g903\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>Thought: Click on \"g903\" to select the first entry from the search results displayed in the suggestion box.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [152, 314]}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry to view details about the Logitech G903 gaming mouse before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [392, 554]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_9.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_10.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_11.png"
] | 6,460
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click on \"g903\" to select the first entry from the search results displayed in the suggestion box.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [152, 314]}<image>Thought: Click the first entry to view details about the Logitech G903 gaming mouse before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [392, 554]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products or details related to \"logitech g903.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_10.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_11.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_12.png"
] | 6,461
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the first entry to view details about the Logitech G903 gaming mouse before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [392, 554]}<image>Thought: Scroll down to view more products or details related to \"logitech g903.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to proceed with adding the Logitech G903 to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 1261]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_11.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_12.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_13.png"
] | 6,462
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Search for \"logitech g903\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more products or details related to \"logitech g903.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to proceed with adding the Logitech G903 to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 1261]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task by confirming your shopping cart shows the Logitech G903, indicating it has been successfully added.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4631647478039173168_12.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_13.png",
"training_data/AITW/aitw_images/webshopping/4631647478039173168_14.png"
] | 6,463
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Click Google to access the internet and navigate to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 1345]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_0.png"
] | 6,464
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click Google to access the internet and navigate to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 1345]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" to search for the Walmart website or app in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_0.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_1.png"
] | 6,465
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click Google to access the internet and navigate to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 1345]}<image>Thought: Type \"walmart\" to search for the Walmart website or app in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Walmart to navigate to the shopping site for managing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 246]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_0.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_1.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_2.png"
] | 6,466
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Type \"walmart\" to search for the Walmart website or app in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click on Walmart to navigate to the shopping site for managing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 246]}<image>",
"role": "user"
},
{
"content": "Thought: Click on everything to navigate the Walmart GUI and find your shopping cart. Search for \"MacBook Pro 13 inch\" using the search bar. Click on search results to see options available for purchase. Add the MacBook Pro to your cart by clicking the appropriate option. Revisit your cart after adding items and look for options to empty it if necessary.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 339]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_1.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_2.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_3.png"
] | 6,467
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click on Walmart to navigate to the shopping site for managing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 246]}<image>Thought: Click on everything to navigate the Walmart GUI and find your shopping cart. Search for \"MacBook Pro 13 inch\" using the search bar. Click on search results to see options available for purchase. Add the MacBook Pro to your cart by clicking the appropriate option. Revisit your cart after adding items and look for options to empty it if necessary.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 339]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 13\" in the search bar to find the desired item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_2.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_3.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_4.png"
] | 6,468
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click on everything to navigate the Walmart GUI and find your shopping cart. Search for \"MacBook Pro 13 inch\" using the search bar. Click on search results to see options available for purchase. Add the MacBook Pro to your cart by clicking the appropriate option. Revisit your cart after adding items and look for options to empty it if necessary.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 339]}<image>Thought: Type \"macbook pro 13\" in the search bar to find the desired item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"inch\" to refine the search for the MacBook Pro 13 inch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 289]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_3.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_4.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_5.png"
] | 6,469
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Type \"macbook pro 13\" in the search bar to find the desired item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13\", \"position\": null}<image>Thought: Click on \"inch\" to refine the search for the MacBook Pro 13 inch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 289]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"X\" to remove items from the shopping cart and proceed with a fresh search for the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1149]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_4.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_5.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_6.png"
] | 6,470
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click on \"inch\" to refine the search for the MacBook Pro 13 inch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 289]}<image>Thought: Click the \"X\" to remove items from the shopping cart and proceed with a fresh search for the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1149]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"8GB RAM Mac OS 128GB\" item to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [493, 1012]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_5.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_6.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_7.png"
] | 6,471
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click the \"X\" to remove items from the shopping cart and proceed with a fresh search for the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1149]}<image>Thought: Click on the \"8GB RAM Mac OS 128GB\" item to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [493, 1012]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" on the MacBook Pro product to include it in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [602, 1332]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_6.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_7.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_8.png"
] | 6,472
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click on the \"8GB RAM Mac OS 128GB\" item to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [493, 1012]}<image>Thought: Click \"Add to cart\" on the MacBook Pro product to include it in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [602, 1332]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to dismiss the protection plan prompt after adding the MacBook Pro to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [670, 407]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_7.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_8.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_9.png"
] | 6,473
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add macbook pro 13 inch to the cart on walmart<image>Thought: Click \"Add to cart\" on the MacBook Pro product to include it in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [602, 1332]}<image>Thought: Click the X to dismiss the protection plan prompt after adding the MacBook Pro to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [670, 407]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task by successfully adding the MacBook Pro to your shopping cart on Walmart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/802911316031266129_8.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_9.png",
"training_data/AITW/aitw_images/webshopping/802911316031266129_10.png"
] | 6,474
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Close the error message to return to Walmart and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 603]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_0.png"
] | 6,475
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Close the error message to return to Walmart and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 603]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to access the Walmart app or website for managing the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_0.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_1.png"
] | 6,476
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Close the error message to return to Walmart and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 603]}<image>Thought: Scroll down to access the Walmart app or website for managing the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Chrome to open the browser and access Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 429]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_0.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_1.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_2.png"
] | 6,477
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Scroll down to access the Walmart app or website for managing the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on Chrome to open the browser and access Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 429]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for Logitech G910 on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 171]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_1.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_2.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_3.png"
] | 6,478
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click on Chrome to open the browser and access Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 429]}<image>Thought: Click the magnifying glass to initiate a search for Logitech G910 on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 171]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to view the items currently in the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 146]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_2.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_3.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_4.png"
] | 6,479
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click the magnifying glass to initiate a search for Logitech G910 on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 171]}<image>Thought: Click SHOPPING CART to view the items currently in the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 146]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see the items in the cart and access the option to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_3.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_4.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_5.png"
] | 6,480
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click SHOPPING CART to view the items currently in the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 146]}<image>Thought: Scroll down to see the items in the cart and access the option to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You need to remove items from the cart first before adding new products. Click on \"Remove\" to clear the current item. This will help you start fresh with your cart for adding Logitech G910.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 422]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_4.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_5.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_6.png"
] | 6,481
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Scroll down to see the items in the cart and access the option to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You need to remove items from the cart first before adding new products. Click on \"Remove\" to clear the current item. This will help you start fresh with your cart for adding Logitech G910.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 422]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to access search options for adding products to the cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 85]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_5.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_6.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_7.png"
] | 6,482
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: You need to remove items from the cart first before adding new products. Click on \"Remove\" to clear the current item. This will help you start fresh with your cart for adding Logitech G910.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 422]}<image>Thought: Click the Search bar to access search options for adding products to the cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 85]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find \"logitech g910\" since it is necessary to locate the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_6.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_7.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_8.png"
] | 6,483
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click the Search bar to access search options for adding products to the cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 85]}<image>Thought: Type in the search bar to find \"logitech g910\" since it is necessary to locate the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"logitech g910\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_7.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_8.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_9.png"
] | 6,484
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Type in the search bar to find \"logitech g910\" since it is necessary to locate the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}<image>Thought: Press enter to execute the search for \"logitech g910\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button to add the Logitech G910 to the cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 926]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_8.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_9.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_10.png"
] | 6,485
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Press enter to execute the search for \"logitech g910\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the PLUS button to add the Logitech G910 to the cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 926]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS to increase the quantity of Logitech G910 in the cart, confirming it's added properly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 906]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_9.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_10.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_11.png"
] | 6,486
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click the PLUS button to add the Logitech G910 to the cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 926]}<image>Thought: Click the PLUS to increase the quantity of Logitech G910 in the cart, confirming it's added properly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 906]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access your current cart items for review.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [479, 137]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_10.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_11.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_12.png"
] | 6,487
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add logitech g910 to the cart on walmart<image>Thought: Click the PLUS to increase the quantity of Logitech G910 in the cart, confirming it's added properly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 906]}<image>Thought: Click SHOPPING CART to access your current cart items for review.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [479, 137]}<image>",
"role": "user"
},
{
"content": "Thought: Confirm that the user successfully added the Logitech G910 to their cart by checking the status as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16078263343431056264_11.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_12.png",
"training_data/AITW/aitw_images/webshopping/16078263343431056264_13.png"
] | 6,488
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>",
"role": "user"
},
{
"content": "Thought: Click on the NAV BAR CIRCLE to access your apps. You need to open your browser or app for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1383]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_0.png"
] | 6,489
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>Thought: Click on the NAV BAR CIRCLE to access your apps. You need to open your browser or app for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1383]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg\" to find the shopping cart option on the app.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_0.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_1.png"
] | 6,490
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>Thought: Click on the NAV BAR CIRCLE to access your apps. You need to open your browser or app for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1383]}<image>Thought: Type \"newegg\" to find the shopping cart option on the app.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"newegg promo code\" to explore potential discounts before proceeding with the cart addition.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 155]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_0.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_1.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_2.png"
] | 6,491
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>Thought: Type \"newegg\" to find the shopping cart option on the app.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>Thought: Click on \"newegg promo code\" to explore potential discounts before proceeding with the cart addition.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 155]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Newegg.com link to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_1.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_2.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_3.png"
] | 6,492
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>Thought: Click on \"newegg promo code\" to explore potential discounts before proceeding with the cart addition.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 155]}<image>Thought: Click the Newegg.com link to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin searching for \"razer naga\" on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [221, 264]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_2.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_3.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_4.png"
] | 6,493
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on newegg. Add \"razer naga\" to the cart on newegg<image>Thought: Click the Newegg.com link to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}<image>Thought: Click the search bar to begin searching for \"razer naga\" on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [221, 264]}<image>",
"role": "user"
},
{
"content": "Thought: You likely completed the task by verifying the shopping cart reflects the \"razer naga\" item successfully added.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4697425841917111350_3.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_4.png",
"training_data/AITW/aitw_images/webshopping/4697425841917111350_5.png"
] | 6,494
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on bestbuy.com. Add razer naga to the cart on bestbuy.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the back button to return to the previous screen in the browser and access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 553]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17332942276201238763_0.png"
] | 6,495
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on bestbuy.com. Add razer naga to the cart on bestbuy.com, then select checkout.<image>Thought: Click the back button to return to the previous screen in the browser and access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 553]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer naga\" to search for the product on bestbuy.com quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17332942276201238763_0.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_1.png"
] | 6,496
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on bestbuy.com. Add razer naga to the cart on bestbuy.com, then select checkout.<image>Thought: Click the back button to return to the previous screen in the browser and access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 553]}<image>Thought: Type \"razer naga\" to search for the product on bestbuy.com quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Razer Naga to open its product page and view details for adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 62]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17332942276201238763_0.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_1.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_2.png"
] | 6,497
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on bestbuy.com. Add razer naga to the cart on bestbuy.com, then select checkout.<image>Thought: Type \"razer naga\" to search for the product on bestbuy.com quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>Thought: Click Razer Naga to open its product page and view details for adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 62]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Pick up tomorrow\" to access the Razer Naga purchase options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [54, 346]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17332942276201238763_1.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_2.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_3.png"
] | 6,498
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on bestbuy.com. Add razer naga to the cart on bestbuy.com, then select checkout.<image>Thought: Click Razer Naga to open its product page and view details for adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 62]}<image>Thought: Click on \"Pick up tomorrow\" to access the Razer Naga purchase options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [54, 346]}<image>",
"role": "user"
},
{
"content": "Thought: The task was completed because the user successfully added the Razer Naga to the cart on bestbuy.com and selected checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17332942276201238763_2.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_3.png",
"training_data/AITW/aitw_images/webshopping/17332942276201238763_4.png"
] | 6,499
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.