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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click the CHAT icon to start a conversation or get support related to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 559]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target\" in the search field to find the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_0.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_1.png"
] | 10,400
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click the CHAT icon to start a conversation or get support related to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 559]}<image>Thought: Type \"target\" in the search field to find the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Target entry to open the website for further searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_0.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_1.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_2.png"
] | 10,401
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Type \"target\" in the search field to find the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>Thought: Click on the Target entry to open the website for further searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 70]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Target® - Official\" link to access the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 272]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_1.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_2.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_3.png"
] | 10,402
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click on the Target entry to open the website for further searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 70]}<image>Thought: Click on the \"Target® - Official\" link to access the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 272]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate a product search on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 149]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_2.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_3.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_4.png"
] | 10,403
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click on the \"Target® - Official\" link to access the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 272]}<image>Thought: Click the Search bar to initiate a product search on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 149]}<image>",
"role": "user"
},
{
"content": "Thought: Focus on the search bar at the top to enter your query. The entries below show recent searches, which you can ignore.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_3.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_4.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_5.png"
] | 10,404
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click the Search bar to initiate a product search on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 149]}<image>Thought: Focus on the search bar at the top to enter your query. The entries below show recent searches, which you can ignore.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"acer predator\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [69, 108]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_4.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_5.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_6.png"
] | 10,405
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Focus on the search bar at the top to enter your query. The entries below show recent searches, which you can ignore.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: Click on \"acer predator\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [69, 108]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Add to cart\" to add the selected Acer Predator monitor to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 527]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_5.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_6.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_7.png"
] | 10,406
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click on \"acer predator\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [69, 108]}<image>Thought: Click on \"Add to cart\" to add the selected Acer Predator monitor to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 527]}<image>",
"role": "user"
},
{
"content": "Thought: Click X to dismiss any pop-ups and focus on the product details for the Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 85]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_6.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_7.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_8.png"
] | 10,407
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click on \"Add to cart\" to add the selected Acer Predator monitor to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 527]}<image>Thought: Click X to dismiss any pop-ups and focus on the product details for the Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 85]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the selected Acer Predator item in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [189, 523]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_7.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_8.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_9.png"
] | 10,408
|
[
{
"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: Search for acer predator on target.com, select the first entry, and add it to the cart.<image>Thought: Click X to dismiss any pop-ups and focus on the product details for the Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 85]}<image>Thought: Click \"Add to cart\" to include the selected Acer Predator item in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [189, 523]}<image>",
"role": "user"
},
{
"content": "Thought: You added the Acer Predator XB3 monitor to the cart, indicating successful completion of your search and selection process.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1363783675199562107_8.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_9.png",
"training_data/AITW/aitw_images/webshopping/1363783675199562107_10.png"
] | 10,409
|
[
{
"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: Clear all items from cart on newegg.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access other apps.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_0.png"
] | 10,410
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Press home to return to the main screen and access other apps.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the browser app to access Newegg and begin the process of clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 821]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_0.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_1.png"
] | 10,411
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Press home to return to the main screen and access other apps.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the browser app to access Newegg and begin the process of clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 821]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on a specific item to check its availability before clearing your cart. The item is currently unavailable, prompting you to consider alternatives. You should look for options related to clearing the cart back on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 76]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_0.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_1.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_2.png"
] | 10,412
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Click the browser app to access Newegg and begin the process of clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 821]}<image>Thought: You clicked on a specific item to check its availability before clearing your cart. The item is currently unavailable, prompting you to consider alternatives. You should look for options related to clearing the cart back on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 76]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to locate Newegg's website and access the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_1.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_2.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_3.png"
] | 10,413
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: You clicked on a specific item to check its availability before clearing your cart. The item is currently unavailable, prompting you to consider alternatives. You should look for options related to clearing the cart back on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 76]}<image>Thought: Type in the search bar to locate Newegg's website and access the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg\" in the address bar to access the Newegg website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_2.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_3.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_4.png"
] | 10,414
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Type in the search bar to locate Newegg's website and access the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Type \"newegg\" in the address bar to access the Newegg website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Computer Parts link to navigate to your cart. You need access to your cart items for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 157]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_3.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_4.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_5.png"
] | 10,415
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Type \"newegg\" in the address bar to access the Newegg website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>Thought: Click on the Computer Parts link to navigate to your cart. You need access to your cart items for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 157]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"SHOPPING CART\" button to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 130]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_4.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_5.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_6.png"
] | 10,416
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Click on the Computer Parts link to navigate to your cart. You need access to your cart items for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 157]}<image>Thought: Click on the \"SHOPPING CART\" button to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 130]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove items from the cart displayed in the Newegg GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 637]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_5.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_6.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_7.png"
] | 10,417
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Click on the \"SHOPPING CART\" button to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 130]}<image>Thought: Click DELETE to remove items from the cart displayed in the Newegg GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 637]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove the selected item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 549]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_6.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_7.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_8.png"
] | 10,418
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Click DELETE to remove items from the cart displayed in the Newegg GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 637]}<image>Thought: Click DELETE to remove the selected item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 549]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove the item from the cart, achieving the goal of clearing all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [29, 495]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_7.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_8.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_9.png"
] | 10,419
|
[
{
"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: Clear all items from cart on newegg.<image>Thought: Click DELETE to remove the selected item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 549]}<image>Thought: Click DELETE to remove the item from the cart, achieving the goal of clearing all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [29, 495]}<image>",
"role": "user"
},
{
"content": "Thought: The cart is empty, confirming all items have been cleared successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14562071330816115672_8.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_9.png",
"training_data/AITW/aitw_images/webshopping/14562071330816115672_10.png"
] | 10,420
|
[
{
"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: Clear the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the CHAT icon to seek assistance or confirmation related to your cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 508]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_0.png"
] | 10,421
|
[
{
"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: Clear the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the CHAT icon to seek assistance or confirmation related to your cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 508]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely clicked on the Costco website instead of Best Buy, leading to a search for \"razer naga.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 37]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_0.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_1.png"
] | 10,422
|
[
{
"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: Clear the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the CHAT icon to seek assistance or confirmation related to your cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 508]}<image>Thought: The user likely clicked on the Costco website instead of Best Buy, leading to a search for \"razer naga.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 37]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Best Buy in the recent searches to go to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 356]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_0.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_1.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_2.png"
] | 10,423
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: The user likely clicked on the Costco website instead of Best Buy, leading to a search for \"razer naga.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 37]}<image>Thought: Click on Best Buy in the recent searches to go to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 356]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Best Buy option to access the website for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [55, 233]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_1.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_2.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_3.png"
] | 10,424
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click on Best Buy in the recent searches to go to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 356]}<image>Thought: Click the Best Buy option to access the website for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [55, 233]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Best Buy to navigate to the website for further shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 242]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_2.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_3.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_4.png"
] | 10,425
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the Best Buy option to access the website for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [55, 233]}<image>Thought: Click on Best Buy to navigate to the website for further shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 242]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access the current items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 97]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_3.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_4.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_5.png"
] | 10,426
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click on Best Buy to navigate to the website for further shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 242]}<image>Thought: Click the SHOPPING CART to access the current items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 97]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to clear the cart and dismiss the protection plan offer.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 116]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_4.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_5.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_6.png"
] | 10,427
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the SHOPPING CART to access the current items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 97]}<image>Thought: Click the X to clear the cart and dismiss the protection plan offer.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 116]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the items in the cart and access the checkout button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_5.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_6.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_7.png"
] | 10,428
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the X to clear the cart and dismiss the protection plan offer.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 116]}<image>Thought: Scroll down to view the items in the cart and access the checkout button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You clicked \"Remove\" to delete the item from your cart. This indicates you want to clear any unwanted items before proceeding.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 332]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_6.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_7.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_8.png"
] | 10,429
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Scroll down to view the items in the cart and access the checkout button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You clicked \"Remove\" to delete the item from your cart. This indicates you want to clear any unwanted items before proceeding.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 332]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Deal\" button to explore options available for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 38]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_7.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_8.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_9.png"
] | 10,430
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: You clicked \"Remove\" to delete the item from your cart. This indicates you want to clear any unwanted items before proceeding.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 332]}<image>Thought: Click on the \"Deal\" button to explore options available for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 38]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"asus zenbook\" in the search bar to find the item easily.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_8.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_9.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_10.png"
] | 10,431
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click on the \"Deal\" button to explore options available for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 38]}<image>Thought: Type \"asus zenbook\" in the search bar to find the item easily.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"asus zenbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [218, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_9.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_10.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_11.png"
] | 10,432
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Type \"asus zenbook\" in the search bar to find the item easily.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"asus zenbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [218, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results for \"asus zenbook\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_10.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_11.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_12.png"
] | 10,433
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click the magnifying glass to initiate a search for \"asus zenbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [218, 73]}<image>Thought: Scroll down to view more results for \"asus zenbook\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You need to add \"asus zenbook\" to the cart, so click the blue \"Add to Cart\" button on this product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 394]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_11.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_12.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_13.png"
] | 10,434
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Scroll down to view more results for \"asus zenbook\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You need to add \"asus zenbook\" to the cart, so click the blue \"Add to Cart\" button on this product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 394]}<image>",
"role": "user"
},
{
"content": "Thought: Click to access the cart and review the added items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 561]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_12.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_13.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_14.png"
] | 10,435
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: You need to add \"asus zenbook\" to the cart, so click the blue \"Add to Cart\" button on this product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [210, 394]}<image>Thought: Click to access the cart and review the added items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 561]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Checkout button to proceed with purchasing items in your cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 404]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_13.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_14.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_15.png"
] | 10,436
|
[
{
"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 the cart on bestbuy.com. Add \"asus zenbook\" to the cart on bestbuy.com, then select checkout.<image>Thought: Click to access the cart and review the added items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 561]}<image>Thought: Click the Checkout button to proceed with purchasing items in your cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 404]}<image>",
"role": "user"
},
{
"content": "Thought: You initiated the checkout process after clearing the cart and adding \"asus zenbook\". Completing these steps indicates successful checkout on bestbuy.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9637874062735614947_14.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_15.png",
"training_data/AITW/aitw_images/webshopping/9637874062735614947_16.png"
] | 10,437
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: The user pressed home, indicating they may not be on the Walmart app to perform the search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_0.png"
] | 10,438
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible: The user pressed home, indicating they may not be on the Walmart app to perform the search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR RECT to access the browser or app for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 545]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_0.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_1.png"
] | 10,439
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible: The user pressed home, indicating they may not be on the Walmart app to perform the search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR RECT to access the browser or app for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 545]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"walmart\" to open the Walmart website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 142]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_0.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_1.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_2.png"
] | 10,440
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the NAV BAR RECT to access the browser or app for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 545]}<image>Thought: Click on \"walmart\" to open the Walmart website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 142]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Walmart& Official\" to access the official Walmart website for my search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [46, 251]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_1.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_2.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_3.png"
] | 10,441
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"walmart\" to open the Walmart website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 142]}<image>Thought: Click on \"Walmart& Official\" to access the official Walmart website for my search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [46, 251]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to initiate a search for \"macbook pro 13 inch\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 71]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_2.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_3.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_4.png"
] | 10,442
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Walmart& Official\" to access the official Walmart website for my search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [46, 251]}<image>Thought: Click the search bar to initiate a search for \"macbook pro 13 inch\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 71]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 13 inch\" to search for the desired product on the Walmart website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13 inch\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_3.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_4.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_5.png"
] | 10,443
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the search bar to initiate a search for \"macbook pro 13 inch\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 71]}<image>Thought: Type \"macbook pro 13 inch\" to search for the desired product on the Walmart website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13 inch\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"pro 13 inch\" to select the first search result for further details on the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 116]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_4.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_5.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_6.png"
] | 10,444
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"macbook pro 13 inch\" to search for the desired product on the Walmart website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 13 inch\", \"position\": null}<image>Thought: Click on \"pro 13 inch\" to select the first search result for further details on the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 116]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Add\" button to include the first entry in the cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [151, 425]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_5.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_6.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_7.png"
] | 10,445
|
[
{
"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: Search for \"macbook pro 13 inch\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"pro 13 inch\" to select the first search result for further details on the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 116]}<image>Thought: Click on the \"Add\" button to include the first entry in the cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [151, 425]}<image>",
"role": "user"
},
{
"content": "Thought: You completed your search for \"macbook pro 13 inch\" on walmart.com and saw the first product displayed. You selected the first entry because it met your search criteria. You added it to the cart to proceed with purchase. Finally, you chose checkout to finalize your order, confirming that all steps were successful.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3023390528486163455_6.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_7.png",
"training_data/AITW/aitw_images/webshopping/3023390528486163455_8.png"
] | 10,446
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay app icon to open it and view your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [522, 1136]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_0.png"
] | 10,447
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click the eBay app icon to open it and view your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [522, 1136]}<image>",
"role": "user"
},
{
"content": "Thought: You accidentally clicked on amazon.com instead of ebay.com, leading you to the wrong website. Sign in to Amazon by typing your email or phone number. Press continue to access your account, but you cannot view the shopping cart on eBay from here.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [477, 94]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_0.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_1.png"
] | 10,448
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click the eBay app icon to open it and view your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [522, 1136]}<image>Thought: You accidentally clicked on amazon.com instead of ebay.com, leading you to the wrong website. Sign in to Amazon by typing your email or phone number. Press continue to access your account, but you cannot view the shopping cart on eBay from here.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [477, 94]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the eBay link to access the website and start shopping for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 354]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_0.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_1.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_2.png"
] | 10,449
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: You accidentally clicked on amazon.com instead of ebay.com, leading you to the wrong website. Sign in to Amazon by typing your email or phone number. Press continue to access your account, but you cannot view the shopping cart on eBay from here.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [477, 94]}<image>Thought: Click on the eBay link to access the website and start shopping for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 354]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to view items currently in the cart and proceed with your shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [605, 167]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_1.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_2.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_3.png"
] | 10,450
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click on the eBay link to access the website and start shopping for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 354]}<image>Thought: Click the SHOPPING CART icon to view items currently in the cart and proceed with your shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [605, 167]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to search for the Lenovo ThinkPad on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 166]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_2.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_3.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_4.png"
] | 10,451
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click the SHOPPING CART icon to view items currently in the cart and proceed with your shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [605, 167]}<image>Thought: Click the magnifying glass to search for the Lenovo ThinkPad on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 166]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"lenovo thinkpad\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_3.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_4.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_5.png"
] | 10,452
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click the magnifying glass to search for the Lenovo ThinkPad on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 166]}<image>Thought: Type \"lenovo thinkpad\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"lenovo thinkpad\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_4.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_5.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_6.png"
] | 10,453
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Type \"lenovo thinkpad\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}<image>Thought: Press enter to execute the search for \"lenovo thinkpad\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Lenovo Thinkpad to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 1110]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_5.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_6.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_7.png"
] | 10,454
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Press enter to execute the search for \"lenovo thinkpad\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click Lenovo Thinkpad to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 1110]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the full product details of the Lenovo Thinkpad on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_6.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_7.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_8.png"
] | 10,455
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click Lenovo Thinkpad to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 1110]}<image>Thought: Scroll down to view the full product details of the Lenovo Thinkpad on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Lenovo Thinkpad and options for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_7.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_8.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_9.png"
] | 10,456
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Scroll down to view the full product details of the Lenovo Thinkpad on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the Lenovo Thinkpad and options for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to save the Lenovo ThinkPad for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [405, 636]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_8.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_9.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_10.png"
] | 10,457
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Scroll down to view more details about the Lenovo Thinkpad and options for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to save the Lenovo ThinkPad for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [405, 636]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen and check if I can select item variations before adding to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_9.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_10.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_11.png"
] | 10,458
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click \"Add to cart\" to save the Lenovo ThinkPad for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [405, 636]}<image>Thought: Press back to return to the previous screen and check if I can select item variations before adding to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Lenovo ThinkPad in the search results displayed on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_10.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_11.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_12.png"
] | 10,459
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Press back to return to the previous screen and check if I can select item variations before adding to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the Lenovo ThinkPad in the search results displayed on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the DISCOUNT to view potential savings or offers for the Lenovo Thinkpad.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 972]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_11.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_12.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_13.png"
] | 10,460
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Scroll down to find the Lenovo ThinkPad in the search results displayed on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the DISCOUNT to view potential savings or offers for the Lenovo Thinkpad.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 972]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details and find the option to add the Lenovo Thinkpad to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_12.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_13.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_14.png"
] | 10,461
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click on the DISCOUNT to view potential savings or offers for the Lenovo Thinkpad.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [76, 972]}<image>Thought: Scroll down to view more details and find the option to add the Lenovo Thinkpad to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the Lenovo Thinkpad in your shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 891]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_13.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_14.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_15.png"
] | 10,462
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Scroll down to view more details and find the option to add the Lenovo Thinkpad to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the Lenovo Thinkpad in your shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 891]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View in cart\" to review the items I want to purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 891]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_14.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_15.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_16.png"
] | 10,463
|
[
{
"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: View the shopping cart on ebay.com. Add lenovo thinkpad to the cart on ebay.com<image>Thought: Click \"Add to cart\" to include the Lenovo Thinkpad in your shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 891]}<image>Thought: Click \"View in cart\" to review the items I want to purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 891]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully viewed the shopping cart on ebay.com. The Lenovo Thinkpad Yoga is now in your cart, confirming your intended purchase.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2331162592553376161_15.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_16.png",
"training_data/AITW/aitw_images/webshopping/2331162592553376161_17.png"
] | 10,464
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to open the browser and start searching for \"logitech g903\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 1136]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_0.png"
] | 10,465
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the Chrome icon to open the browser and start searching for \"logitech g903\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 1136]}<image>",
"role": "user"
},
{
"content": "Thought: Select \"Deliver to Netherlands\" to ensure the shipping address is correct for the intended item purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 288]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_0.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_1.png"
] | 10,466
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the Chrome icon to open the browser and start searching for \"logitech g903\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 1136]}<image>Thought: Select \"Deliver to Netherlands\" to ensure the shipping address is correct for the intended item purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 288]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g903\" in the Amazon search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_0.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_1.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_2.png"
] | 10,467
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Select \"Deliver to Netherlands\" to ensure the shipping address is correct for the intended item purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 288]}<image>Thought: Type \"logitech g903\" in the Amazon search bar to find the desired product.\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 for detailed information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [182, 340]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_1.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_2.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_3.png"
] | 10,468
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Type \"logitech g903\" in the Amazon search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>Thought: Click on \"g903\" to select the first entry from the search results for detailed information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [182, 340]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to submit the search for \"logitech g903\" and view results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [645, 287]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_2.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_3.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_4.png"
] | 10,469
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on \"g903\" to select the first entry from the search results for detailed information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [182, 340]}<image>Thought: Click the magnifying glass to submit the search for \"logitech g903\" and view results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [645, 287]}<image>",
"role": "user"
},
{
"content": "Thought: Click Filters to refine search results for \"logitech g903\" and find the desired product more easily.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [557, 498]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_3.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_4.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_5.png"
] | 10,470
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to submit the search for \"logitech g903\" and view results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [645, 287]}<image>Thought: Click Filters to refine search results for \"logitech g903\" and find the desired product more easily.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [557, 498]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g903\" since the initial screen only shows a few items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_4.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_5.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_6.png"
] | 10,471
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click Filters to refine search results for \"logitech g903\" and find the desired product more easily.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [557, 498]}<image>Thought: Scroll down to view more search results for \"logitech g903\" since the initial screen only shows a few items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more search results for \"logitech g903\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_5.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_6.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_7.png"
] | 10,472
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"logitech g903\" since the initial screen only shows a few items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more search results for \"logitech g903\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Charging\" to filter results related to the Logitech G903, focusing on charging options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [532, 598]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_6.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_7.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_8.png"
] | 10,473
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to see more search results for \"logitech g903\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Charging\" to filter results related to the Logitech G903, focusing on charging options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [532, 598]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Gaming\" category to find relevant products. This operation targets the category that likely contains gaming mice such as Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1081]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_7.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_8.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_9.png"
] | 10,474
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click \"Charging\" to filter results related to the Logitech G903, focusing on charging options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [532, 598]}<image>Thought: Click on the \"Gaming\" category to find relevant products. This operation targets the category that likely contains gaming mice such as Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1081]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g903\" on Amazon's interface.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_8.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_9.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_10.png"
] | 10,475
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on the \"Gaming\" category to find relevant products. This operation targets the category that likely contains gaming mice such as Logitech G903.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1081]}<image>Thought: Scroll down to view more search results for \"logitech g903\" on Amazon's interface.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Logitech G903\" entry to further explore the product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [481, 858]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_9.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_10.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_11.png"
] | 10,476
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"logitech g903\" on Amazon's interface.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"Logitech G903\" entry to further explore the product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [481, 858]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to \"logitech g903\" since the current screen shows limited options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_10.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_11.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_12.png"
] | 10,477
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on the \"Logitech G903\" entry to further explore the product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [481, 858]}<image>Thought: Scroll down to view more products related to \"logitech g903\" since the current screen shows limited options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Logitech G903.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_11.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_12.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_13.png"
] | 10,478
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more products related to \"logitech g903\" since the current screen shows limited options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the Logitech G903.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Cart button to proceed with adding the item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [463, 857]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_12.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_13.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_14.png"
] | 10,479
|
[
{
"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: Search for \"logitech g903\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the Logitech G903.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Cart button to proceed with adding the item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [463, 857]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates that the user has successfully searched for \"logitech g903,\" found it in their cart, and added it to their purchases.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17149277379105535668_13.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_14.png",
"training_data/AITW/aitw_images/webshopping/17149277379105535668_15.png"
] | 10,480
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay app icon on the home screen to open it for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 868]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_0.png"
] | 10,481
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click the eBay app icon on the home screen to open it for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 868]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: You are on the Amazon sign-in page instead of eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 72]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_0.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_1.png"
] | 10,482
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click the eBay app icon on the home screen to open it for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 868]}<image>Thought: Status task impossible: You are on the Amazon sign-in page instead of eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 72]}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 231]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_0.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_1.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_2.png"
] | 10,483
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Status task impossible: You are on the Amazon sign-in page instead of eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 72]}<image>Thought: Click the eBay link to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 231]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for anything\" to access the search bar and enter the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 219]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_1.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_2.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_3.png"
] | 10,484
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click the eBay link to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 231]}<image>Thought: Click on \"Search for anything\" to access the search bar and enter the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 219]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell xps\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_2.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_3.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_4.png"
] | 10,485
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click on \"Search for anything\" to access the search bar and enter the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 219]}<image>Thought: Type \"dell xps\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 205]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_3.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_4.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_5.png"
] | 10,486
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Type \"dell xps\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 205]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results for \"dell xps\" before adding items to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_4.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_5.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_6.png"
] | 10,487
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click the magnifying glass to initiate a search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 205]}<image>Thought: Scroll down to view more results for \"dell xps\" before adding items to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"i7-6600U 8GB Read!!!\" to view details of the laptop.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [268, 639]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_5.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_6.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_7.png"
] | 10,488
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Scroll down to view more results for \"dell xps\" before adding items to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"i7-6600U 8GB Read!!!\" to view details of the laptop.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [268, 639]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the \"Dell XPS 13\" since it may help in determining its features.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_6.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_7.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_8.png"
] | 10,489
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Click on the \"i7-6600U 8GB Read!!!\" to view details of the laptop.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [268, 639]}<image>Thought: Scroll down to view more details about the \"Dell XPS 13\" since it may help in determining its features.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to save the item for potential purchase later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [248, 849]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_7.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_8.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_9.png"
] | 10,490
|
[
{
"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: Add \"dell xps\" to the cart on ebay<image>Thought: Scroll down to view more details about the \"Dell XPS 13\" since it may help in determining its features.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to save the item for potential purchase later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [248, 849]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully added \"dell xps\" to the cart, confirming the task completion.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16656933246507711720_8.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_9.png",
"training_data/AITW/aitw_images/webshopping/16656933246507711720_10.png"
] | 10,491
|
[
{
"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: Clear the shopping cart on newegg.com.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the shopping cart on Newegg's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_0.png"
] | 10,492
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Scroll down to view the shopping cart on Newegg's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Google to open the browser and access Newegg.com for clearing the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 559]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_0.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_1.png"
] | 10,493
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Scroll down to view the shopping cart on Newegg's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click Google to open the browser and access Newegg.com for clearing the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 559]}<image>",
"role": "user"
},
{
"content": "Thought: You are currently on a Google search page and want to access Walmart to find products. Clicking \"Walmart\" helps navigate towards the shopping options available on their site. However, this does not directly assist in clearing the shopping cart on Newegg.com. To complete your task, you should go back and navigate directly to Newegg instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 223]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_0.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_1.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_2.png"
] | 10,494
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Click Google to open the browser and access Newegg.com for clearing the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [362, 559]}<image>Thought: You are currently on a Google search page and want to access Walmart to find products. Clicking \"Walmart\" helps navigate towards the shopping options available on their site. However, this does not directly assist in clearing the shopping cart on Newegg.com. To complete your task, you should go back and navigate directly to Newegg instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 223]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove items from the shopping cart on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_1.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_2.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_3.png"
] | 10,495
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: You are currently on a Google search page and want to access Walmart to find products. Clicking \"Walmart\" helps navigate towards the shopping options available on their site. However, this does not directly assist in clearing the shopping cart on Newegg.com. To complete your task, you should go back and navigate directly to Newegg instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [298, 223]}<image>Thought: Click the X to remove items from the shopping cart on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 70]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" to navigate directly to the shopping cart page on the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_2.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_3.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_4.png"
] | 10,496
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Click the X to remove items from the shopping cart on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 70]}<image>Thought: Type \"newegg.com\" to navigate directly to the shopping cart page on the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Computer Parts, PC Comp..Computers, LED LCD ...\" to navigate to the shopping cart page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 158]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_3.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_4.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_5.png"
] | 10,497
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Type \"newegg.com\" to navigate directly to the shopping cart page on the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Click on \"Computer Parts, PC Comp..Computers, LED LCD ...\" to navigate to the shopping cart page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 158]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the pop-up window and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [442, 364]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_4.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_5.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_6.png"
] | 10,498
|
[
{
"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: Clear the shopping cart on newegg.com.<image>Thought: Click on \"Computer Parts, PC Comp..Computers, LED LCD ...\" to navigate to the shopping cart page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 158]}<image>Thought: Click the X to close the pop-up window and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [442, 364]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"SHOPPING CART\" icon to access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [450, 144]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11085494667859062180_5.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_6.png",
"training_data/AITW/aitw_images/webshopping/11085494667859062180_7.png"
] | 10,499
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.