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: Clear all items from cart on costco. Search for asus zenbook on costco, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the first entry of the search results for \"asus zenbook.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down the screen to view the available items for \"asus zenbook.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the ASUS Zenbook entry to select it for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [401, 639]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8873756622386945493_12.png",
"training_data/AITW/aitw_images/webshopping/8873756622386945493_13.png",
"training_data/AITW/aitw_images/webshopping/8873756622386945493_14.png"
] | 7,400
|
[
{
"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: Clear all items from cart on costco. Search for asus zenbook on costco, select the first entry, and add it to the cart.<image>Thought: Scroll down the screen to view the available items for \"asus zenbook.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the ASUS Zenbook entry to select it for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [401, 639]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the task of clearing all items from the cart on Costco by successfully searching for and adding the ASUS Zenbook to your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8873756622386945493_13.png",
"training_data/AITW/aitw_images/webshopping/8873756622386945493_14.png",
"training_data/AITW/aitw_images/webshopping/8873756622386945493_15.png"
] | 7,401
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Walmart app or website, as it's likely not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_0.png"
] | 7,402
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Scroll down to find the Walmart app or website, as it's likely not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click GOOGLE to open the browser and navigate to walmart.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [43, 346]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_0.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_1.png"
] | 7,403
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Scroll down to find the Walmart app or website, as it's likely not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click GOOGLE to open the browser and navigate to walmart.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [43, 346]}<image>",
"role": "user"
},
{
"content": "Thought: Click Google to access the search engine for finding walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 108]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_0.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_1.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_2.png"
] | 7,404
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click GOOGLE to open the browser and navigate to walmart.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [43, 346]}<image>Thought: Click Google to access the search engine for finding walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 108]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" to access the Walmart website from the search bar in the GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_1.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_2.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_3.png"
] | 7,405
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click Google to access the search engine for finding walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 108]}<image>Thought: Type \"walmart.com\" to access the Walmart website from the search bar in the GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Walmart.com to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_2.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_3.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_4.png"
] | 7,406
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Type \"walmart.com\" to access the Walmart website from the search bar in the GUI.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click Walmart.com to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Click the shopping cart icon to view its contents on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_3.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_4.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_5.png"
] | 7,407
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click Walmart.com to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 67]}<image>Thought: Click the shopping cart icon to view its contents on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input \"asus rog\" for adding to the cart. After typing, press enter to initiate the search. Scroll through the results to find \"asus rog,\" then click on it to view details. Click \"Add to Cart\" button on the product page, then click on the cart icon to view your current items. Finally, tap \"Continue to checkout\" button to proceed with purchasing items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [137, 81]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_4.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_5.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_6.png"
] | 7,408
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click the shopping cart icon to view its contents on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}<image>Thought: Click the search bar to input \"asus rog\" for adding to the cart. After typing, press enter to initiate the search. Scroll through the results to find \"asus rog,\" then click on it to view details. Click \"Add to Cart\" button on the product page, then click on the cart icon to view your current items. Finally, tap \"Continue to checkout\" button to proceed with purchasing items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [137, 81]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"asus rog\" in the search bar to find the item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_5.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_6.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_7.png"
] | 7,409
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click the search bar to input \"asus rog\" for adding to the cart. After typing, press enter to initiate the search. Scroll through the results to find \"asus rog,\" then click on it to view details. Click \"Add to Cart\" button on the product page, then click on the cart icon to view your current items. Finally, tap \"Continue to checkout\" button to proceed with purchasing items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [137, 81]}<image>Thought: Type \"asus rog\" in the search bar to find the item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"asus rog\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 109]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_6.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_7.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_8.png"
] | 7,410
|
[
{
"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: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Type \"asus rog\" in the search bar to find the item on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}<image>Thought: Click on \"asus rog\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 109]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Add\" button to include the item \"asus rog\" in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 398]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_7.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_8.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_9.png"
] | 7,411
|
[
{
"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: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"asus rog\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [35, 109]}<image>Thought: Click on the \"Add\" button to include the item \"asus rog\" in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 398]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to view the items I have selected for purchase on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 68]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_8.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_9.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_10.png"
] | 7,412
|
[
{
"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: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click on the \"Add\" button to include the item \"asus rog\" in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 398]}<image>Thought: Click SHOPPING CART to view the items I have selected for purchase on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 68]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Continue to checkout\" button to progress towards completing the purchase on the cart screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [121, 517]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_9.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_10.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_11.png"
] | 7,413
|
[
{
"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: Show the shopping cart on walmart.com. Add \"asus rog\" to the cart on walmart.com, then select checkout.<image>Thought: Click SHOPPING CART to view the items I have selected for purchase on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 68]}<image>Thought: Click the \"Continue to checkout\" button to progress towards completing the purchase on the cart screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [121, 517]}<image>",
"role": "user"
},
{
"content": "Thought: You would show the shopping cart by navigating to the cart URL on walmart.com. You would add \"asus rog\" to the cart by searching for it and completing the addition process. You would select checkout to proceed with your purchase after ensuring items are in the cart. The status indicates that you successfully completed these operations on Walmart's website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5420409950517215909_10.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_11.png",
"training_data/AITW/aitw_images/webshopping/5420409950517215909_12.png"
] | 7,414
|
[
{
"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: Search for the best rated headphones on AliExpress.<image>",
"role": "user"
},
{
"content": "Thought: You type in the search bar to initiate a query for headphones on AliExpress.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on AliExpress.\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15821838614659796763_0.png"
] | 7,415
|
[
{
"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: Search for the best rated headphones on AliExpress.<image>Thought: You type in the search bar to initiate a query for headphones on AliExpress.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on AliExpress.\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar on AliExpress to begin searching for headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 185]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15821838614659796763_0.png",
"training_data/AITW/aitw_images/webshopping/15821838614659796763_1.png"
] | 7,416
|
[
{
"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: Search for the best rated headphones on AliExpress.<image>Thought: You type in the search bar to initiate a query for headphones on AliExpress.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on AliExpress.\", \"position\": null}<image>Thought: Click the search bar on AliExpress to begin searching for headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 185]}<image>",
"role": "user"
},
{
"content": "Thought: Click the suggestion for \"the best rated\" to initiate the search for headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [227, 178]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15821838614659796763_0.png",
"training_data/AITW/aitw_images/webshopping/15821838614659796763_1.png",
"training_data/AITW/aitw_images/webshopping/15821838614659796763_2.png"
] | 7,417
|
[
{
"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: Search for the best rated headphones on AliExpress.<image>Thought: Click the search bar on AliExpress to begin searching for headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 185]}<image>Thought: Click the suggestion for \"the best rated\" to initiate the search for headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [227, 178]}<image>",
"role": "user"
},
{
"content": "Thought: The user has successfully searched for \"the best rated headphone\" using the search bar, completing their task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15821838614659796763_1.png",
"training_data/AITW/aitw_images/webshopping/15821838614659796763_2.png",
"training_data/AITW/aitw_images/webshopping/15821838614659796763_3.png"
] | 7,418
|
[
{
"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: search for outdoor chairs on article.com<image>",
"role": "user"
},
{
"content": "Thought: Scroll down the screen to view more content related to outdoor chairs on article.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_0.png"
] | 7,419
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Scroll down the screen to view more content related to outdoor chairs on article.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click A1apps to open the application that allows searching for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 200]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_0.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_1.png"
] | 7,420
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Scroll down the screen to view more content related to outdoor chairs on article.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click A1apps to open the application that allows searching for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 200]}<image>",
"role": "user"
},
{
"content": "Thought: Select the \"best\" option to refine search results for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 61]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_0.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_1.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_2.png"
] | 7,421
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click A1apps to open the application that allows searching for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 200]}<image>Thought: Select the \"best\" option to refine search results for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 61]}<image>",
"role": "user"
},
{
"content": "Thought: You likely clicked on \"table\" to refine your search results towards a specific category related to outdoor furniture.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 27]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_1.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_2.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_3.png"
] | 7,422
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Select the \"best\" option to refine search results for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 61]}<image>Thought: You likely clicked on \"table\" to refine your search results towards a specific category related to outdoor furniture.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 27]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"article.com\" to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"TYPE\", \"value\": \"article.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_2.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_3.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_4.png"
] | 7,423
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: You likely clicked on \"table\" to refine your search results towards a specific category related to outdoor furniture.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 27]}<image>Thought: Type \"article.com\" to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"TYPE\", \"value\": \"article.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the article.com link to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 65]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_3.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_4.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_5.png"
] | 7,424
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Type \"article.com\" to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"TYPE\", \"value\": \"article.com\", \"position\": null}<image>Thought: Click on the article.com link to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 65]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to initiate a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [85, 87]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_4.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_5.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_6.png"
] | 7,425
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click on the article.com link to navigate to the website for searching outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 65]}<image>Thought: Click the search bar to initiate a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [85, 87]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to initiate a product search on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_5.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_6.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_7.png"
] | 7,426
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click the search bar to initiate a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [85, 87]}<image>Thought: Click the search bar to initiate a product search on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Search for products, pages and help topics...\" bar to begin searching for outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_6.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_7.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_8.png"
] | 7,427
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click the search bar to initiate a product search on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}<image>Thought: Click on the \"Search for products, pages and help topics...\" bar to begin searching for outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin entering a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 89]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_7.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_8.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_9.png"
] | 7,428
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click on the \"Search for products, pages and help topics...\" bar to begin searching for outdoor chairs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 88]}<image>Thought: Click the search bar to begin entering a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 89]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"outdoor chairs\" into the search bar to initiate a search for relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \" outdoor chairs\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_8.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_9.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_10.png"
] | 7,429
|
[
{
"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: search for outdoor chairs on article.com<image>Thought: Click the search bar to begin entering a query for outdoor chairs on article.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 89]}<image>Thought: Type \"outdoor chairs\" into the search bar to initiate a search for relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \" outdoor chairs\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: The user likely typed \"outdoor chairs\" in the search bar to find relevant products. After executing the search, the user reached a page displaying various outdoor chairs available on article.com, indicating successful completion of their task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11774502825785950447_9.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_10.png",
"training_data/AITW/aitw_images/webshopping/11774502825785950447_11.png"
] | 7,430
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Type \"target.com\" to navigate to the Target website and access shopping options.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_0.png"
] | 7,431
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Type \"target.com\" to navigate to the Target website and access shopping options.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to navigate to the target.com website and access my shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_0.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_1.png"
] | 7,432
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Type \"target.com\" to navigate to the Target website and access shopping options.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>Thought: Press enter to navigate to the target.com website and access my shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to access the shopping cart on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_0.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_1.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_2.png"
] | 7,433
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Press enter to navigate to the target.com website and access my shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to access the shopping cart on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Chrome to open the web browser and access target.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 439]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_1.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_2.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_3.png"
] | 7,434
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Scroll down to access the shopping cart on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on Chrome to open the web browser and access target.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 439]}<image>",
"role": "user"
},
{
"content": "Thought: Click the razer blade to view details about the product you want to add to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 163]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_2.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_3.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_4.png"
] | 7,435
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Click on Chrome to open the web browser and access target.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 439]}<image>Thought: Click the razer blade to view details about the product you want to add to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 163]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to enter \"razer huntsman\" for the cart addition on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 163]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_3.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_4.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_5.png"
] | 7,436
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Click the razer blade to view details about the product you want to add to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 163]}<image>Thought: Click the search bar to enter \"razer huntsman\" for the cart addition on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 163]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer huntsman\" in the search bar to find the item on target.com. Then press enter to execute the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 152]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_4.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_5.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_6.png"
] | 7,437
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Click the search bar to enter \"razer huntsman\" for the cart addition on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 163]}<image>Thought: Type \"razer huntsman\" in the search bar to find the item on target.com. Then press enter to execute the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 152]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer huntsman\" into the search bar to find the item on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_5.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_6.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_7.png"
] | 7,438
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Type \"razer huntsman\" in the search bar to find the item on target.com. Then press enter to execute the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 152]}<image>Thought: Type \"razer huntsman\" into the search bar to find the item on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"razer huntsman\" in the target.com search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_6.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_7.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_8.png"
] | 7,439
|
[
{
"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: Show the shopping cart on target.com. Add razer huntsman to the cart on target.com, then select checkout.<image>Thought: Type \"razer huntsman\" into the search bar to find the item on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>Thought: Press enter to execute the search for \"razer huntsman\" in the target.com search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You likely opened Target's website to find the Razer Huntsman keyboard in your shopping cart. You probably added the product to the cart after locating it through the search bar. After that, selecting checkout suggests you want to complete your purchase confidently and quickly. Since all steps were successful, you marked the task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2491352322478993252_7.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_8.png",
"training_data/AITW/aitw_images/webshopping/2491352322478993252_9.png"
] | 7,440
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_0.png"
] | 7,441
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the Google Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_0.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_1.png"
] | 7,442
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the Google Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}<image>Thought: Click the Google Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}<image>",
"role": "user"
},
{
"content": "Thought: Click the item to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 395]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_0.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_1.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_2.png"
] | 7,443
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the Google Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1165]}<image>Thought: Click the item to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 395]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g502\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g502\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_1.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_2.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_3.png"
] | 7,444
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the item to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 395]}<image>Thought: Type \"logitech g502\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g502\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"logitech g502\" on target.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_2.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_3.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_4.png"
] | 7,445
|
[
{
"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 logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"logitech g502\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g502\", \"position\": null}<image>Thought: Press enter to initiate the search for \"logitech g502\" on target.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for the logitech g502 on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_3.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_4.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_5.png"
] | 7,446
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Press enter to initiate the search for \"logitech g502\" on target.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for the logitech g502 on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" after confirming the desired product is the Logitech G502 HERO Wired Gaming Mouse.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [499, 774]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_4.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_5.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_6.png"
] | 7,447
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more search results for the logitech g502 on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" after confirming the desired product is the Logitech G502 HERO Wired Gaming Mouse.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [499, 774]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see the added item details and the option to proceed with checkout.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_5.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_6.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_7.png"
] | 7,448
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"Add to cart\" after confirming the desired product is the Logitech G502 HERO Wired Gaming Mouse.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [499, 774]}<image>Thought: Scroll down to see the added item details and the option to proceed with checkout.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Protect your purchase\" button to add a protection plan for the item before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 611]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_6.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_7.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_8.png"
] | 7,449
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to see the added item details and the option to proceed with checkout.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Protect your purchase\" button to add a protection plan for the item before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 611]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View cart & check out\" to proceed with the checkout process for my added items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [395, 545]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_7.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_8.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_9.png"
] | 7,450
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the \"Protect your purchase\" button to add a protection plan for the item before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 611]}<image>Thought: Click \"View cart & check out\" to proceed with the checkout process for my added items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [395, 545]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Sign in to checkout\" to proceed with the payment process after adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [452, 1341]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_8.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_9.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_10.png"
] | 7,451
|
[
{
"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: Search for logitech g502 on target.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"View cart & check out\" to proceed with the checkout process for my added items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [395, 545]}<image>Thought: Click on \"Sign in to checkout\" to proceed with the payment process after adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [452, 1341]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the task since you reached the checkout screen after adding the Logitech G502 to your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5033022097945049517_9.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_10.png",
"training_data/AITW/aitw_images/webshopping/5033022097945049517_11.png"
] | 7,452
|
[
{
"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: Search for the best selling video games at Target<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app where I can search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 512]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_0.png"
] | 7,453
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Click PLAY to open the app where I can search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 512]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that the current page is not related to video games; instead, it features rugs. Click on the search bar at the top to start a search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 53]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_0.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_1.png"
] | 7,454
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Click PLAY to open the app where I can search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 512]}<image>Thought: Recognize that the current page is not related to video games; instead, it features rugs. Click on the search bar at the top to start a search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 53]}<image>",
"role": "user"
},
{
"content": "Thought: You type \"Target\" in the search bar to begin your search for the best selling video games there.\nAction: {\"action\": \"TYPE\", \"value\": \"Target\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_0.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_1.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_2.png"
] | 7,455
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Recognize that the current page is not related to video games; instead, it features rugs. Click on the search bar at the top to start a search for video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 53]}<image>Thought: You type \"Target\" in the search bar to begin your search for the best selling video games there.\nAction: {\"action\": \"TYPE\", \"value\": \"Target\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Target to access the store's information and find video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 217]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_1.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_2.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_3.png"
] | 7,456
|
[
{
"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: Search for the best selling video games at Target<image>Thought: You type \"Target\" in the search bar to begin your search for the best selling video games there.\nAction: {\"action\": \"TYPE\", \"value\": \"Target\", \"position\": null}<image>Thought: Click on Target to access the store's information and find video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 217]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Target link to access their website for browsing video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 480]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_2.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_3.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_4.png"
] | 7,457
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Click on Target to access the store's information and find video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [108, 217]}<image>Thought: Click on the Target link to access their website for browsing video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 480]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to begin entering your query for best selling video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [88, 299]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_3.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_4.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_5.png"
] | 7,458
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Click on the Target link to access their website for browsing video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 480]}<image>Thought: Click the Search bar to begin entering your query for best selling video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [88, 299]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"best selling video games\" in the search bar to find relevant results for video games at Target.\nAction: {\"action\": \"TYPE\", \"value\": \"best selling video games\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_4.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_5.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_6.png"
] | 7,459
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Click the Search bar to begin entering your query for best selling video games.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [88, 299]}<image>Thought: Type \"best selling video games\" in the search bar to find relevant results for video games at Target.\nAction: {\"action\": \"TYPE\", \"value\": \"best selling video games\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 157]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_5.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_6.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_7.png"
] | 7,460
|
[
{
"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: Search for the best selling video games at Target<image>Thought: Type \"best selling video games\" in the search bar to find relevant results for video games at Target.\nAction: {\"action\": \"TYPE\", \"value\": \"best selling video games\", \"position\": null}<image>Thought: Click the magnifying glass to access the search function on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 157]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully searched for the best selling video games using the search bar on Target's app.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7107074769144991759_6.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_7.png",
"training_data/AITW/aitw_images/webshopping/7107074769144991759_8.png"
] | 7,461
|
[
{
"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: Add razer kraken to the cart on amazon<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome icon to open the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1227]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_0.png"
] | 7,462
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click the Google Chrome icon to open the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1227]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: You cannot add Razer Kraken to the cart because you are currently on Newegg's verification page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 88]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_0.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_1.png"
] | 7,463
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click the Google Chrome icon to open the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [436, 1227]}<image>Thought: Status task impossible: You cannot add Razer Kraken to the cart because you are currently on Newegg's verification page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 88]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon\" in the search bar to access the Amazon website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_0.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_1.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_2.png"
] | 7,464
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Status task impossible: You cannot add Razer Kraken to the cart because you are currently on Newegg's verification page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 88]}<image>Thought: Type \"amazon\" in the search bar to access the Amazon website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Smile more\" to access the Amazon homepage for further shopping options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [501, 154]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_1.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_2.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_3.png"
] | 7,465
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Type \"amazon\" in the search bar to access the Amazon website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>Thought: Click on \"Smile more\" to access the Amazon homepage for further shopping options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [501, 154]}<image>",
"role": "user"
},
{
"content": "Thought: Cancel the removal of the suggestion to continue with the search for Razer Kraken on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [437, 792]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_2.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_3.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_4.png"
] | 7,466
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click on \"Smile more\" to access the Amazon homepage for further shopping options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [501, 154]}<image>Thought: Cancel the removal of the suggestion to continue with the search for Razer Kraken on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [437, 792]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Spend less\" option to access discounts and deals on Amazon for potential savings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_3.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_4.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_5.png"
] | 7,467
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Cancel the removal of the suggestion to continue with the search for Razer Kraken on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [437, 792]}<image>Thought: Click the \"Spend less\" option to access discounts and deals on Amazon for potential savings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Best Sellers\" to find popular products, including the Razer Kraken headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 234]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_4.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_5.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_6.png"
] | 7,468
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click the \"Spend less\" option to access discounts and deals on Amazon for potential savings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 184]}<image>Thought: Click \"Best Sellers\" to find popular products, including the Razer Kraken headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 234]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer kraken\" in the search bar to find the specific product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_5.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_6.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_7.png"
] | 7,469
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click \"Best Sellers\" to find popular products, including the Razer Kraken headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 234]}<image>Thought: Type \"razer kraken\" in the search bar to find the specific product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"razer kraken\" in the Amazon search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_6.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_7.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_8.png"
] | 7,470
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Type \"razer kraken\" in the search bar to find the specific product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>Thought: Press enter to execute the search for \"razer kraken\" in the Amazon search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Razer Kraken Gaming headset to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [433, 503]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_7.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_8.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_9.png"
] | 7,471
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Press enter to execute the search for \"razer kraken\" in the Amazon search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the Razer Kraken Gaming headset to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [433, 503]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products and locate the Razer Kraken headset listing on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_8.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_9.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_10.png"
] | 7,472
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Click the Razer Kraken Gaming headset to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [433, 503]}<image>Thought: Scroll down to view more products and locate the Razer Kraken headset listing on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional details about the Razer Kraken headset or the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_9.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_10.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_11.png"
] | 7,473
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Scroll down to view more products and locate the Razer Kraken headset listing on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view additional details about the Razer Kraken headset or the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to initiate the process of purchasing the Razer Kraken.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [472, 698]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_10.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_11.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_12.png"
] | 7,474
|
[
{
"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: Add razer kraken to the cart on amazon<image>Thought: Scroll down to view additional details about the Razer Kraken headset or the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to initiate the process of purchasing the Razer Kraken.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [472, 698]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates that the user successfully added the Razer Kraken to their cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6089343506526452731_11.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_12.png",
"training_data/AITW/aitw_images/webshopping/6089343506526452731_13.png"
] | 7,475
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the Newegg app after encountering an error.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_0.png"
] | 7,476
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Press home to exit the Newegg app after encountering an error.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Open the Newegg app to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 469]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_0.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_1.png"
] | 7,477
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Press home to exit the Newegg app after encountering an error.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Open the Newegg app to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 469]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return from the checkout screen to access the cart and remove items.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_0.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_1.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_2.png"
] | 7,478
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Open the Newegg app to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 469]}<image>Thought: Press back to return from the checkout screen to access the cart and remove items.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"dell xps\" on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [209, 72]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_1.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_2.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_3.png"
] | 7,479
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Press back to return from the checkout screen to access the cart and remove items.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"dell xps\" on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [209, 72]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the keyword search bar to enter the desired product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 74]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_2.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_3.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_4.png"
] | 7,480
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click the magnifying glass to initiate a search for \"dell xps\" on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [209, 72]}<image>Thought: Click on the keyword search bar to enter the desired product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 74]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell xps\" into the search bar to find the desired item on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_3.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_4.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_5.png"
] | 7,481
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click on the keyword search bar to enter the desired product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 74]}<image>Thought: Type \"dell xps\" into the search bar to find the desired item on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to confirm the search for \"dell xps\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_4.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_5.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_6.png"
] | 7,482
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Type \"dell xps\" into the search bar to find the desired item on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>Thought: Press enter to confirm the search for \"dell xps\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"dell xps\" to find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_5.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_6.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_7.png"
] | 7,483
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Press enter to confirm the search for \"dell xps\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for \"dell xps\" to find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Dell XPS 8940\" to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 329]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_6.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_7.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_8.png"
] | 7,484
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Scroll down to view more search results for \"dell xps\" to find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"Dell XPS 8940\" to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 329]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"ADD TO CART\" to add the Dell XPS to your cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 554]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_7.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_8.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_9.png"
] | 7,485
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click on \"Dell XPS 8940\" to view its details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 329]}<image>Thought: Click \"ADD TO CART\" to add the Dell XPS to your cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 554]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access the items in the cart for review before clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [24, 547]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_8.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_9.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_10.png"
] | 7,486
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click \"ADD TO CART\" to add the Dell XPS to your cart from the product page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [134, 554]}<image>Thought: Click SHOPPING CART to access the items in the cart for review before clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [24, 547]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove the Razer Naga mouse from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [21, 293]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_9.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_10.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_11.png"
] | 7,487
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click SHOPPING CART to access the items in the cart for review before clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [24, 547]}<image>Thought: Click DELETE to remove the Razer Naga mouse from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [21, 293]}<image>",
"role": "user"
},
{
"content": "Thought: Click SECURE CHECKOUT to proceed with the payment for the Dell XPS in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 515]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_10.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_11.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_12.png"
] | 7,488
|
[
{
"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: Clear all items from cart on newegg. Add \"dell xps\" to the cart on newegg, then select checkout.<image>Thought: Click DELETE to remove the Razer Naga mouse from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [21, 293]}<image>Thought: Click SECURE CHECKOUT to proceed with the payment for the Dell XPS in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 515]}<image>",
"role": "user"
},
{
"content": "Thought: You appear to have successfully completed your task of clearing the cart and checking out on Newegg.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12824252983084095914_11.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_12.png",
"training_data/AITW/aitw_images/webshopping/12824252983084095914_13.png"
] | 7,489
|
[
{
"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 usb-b to the cart on newegg, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the Newegg app icon to open it and proceed with adding the USB-B to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 473]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12026873749749305645_0.png"
] | 7,490
|
[
{
"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 usb-b to the cart on newegg, then select checkout.<image>Thought: Click the Newegg app icon to open it and proceed with adding the USB-B to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 473]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the search bar and return to the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 144]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12026873749749305645_0.png",
"training_data/AITW/aitw_images/webshopping/12026873749749305645_1.png"
] | 7,491
|
[
{
"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: Add usb-b to the cart on newegg, then select checkout.<image>Thought: Click the Newegg app icon to open it and proceed with adding the USB-B to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 473]}<image>Thought: Click the X to close the search bar and return to the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 144]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"usb-b\" in the search bar to find the product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-b\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12026873749749305645_0.png",
"training_data/AITW/aitw_images/webshopping/12026873749749305645_1.png",
"training_data/AITW/aitw_images/webshopping/12026873749749305645_2.png"
] | 7,492
|
[
{
"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: Add usb-b to the cart on newegg, then select checkout.<image>Thought: Click the X to close the search bar and return to the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 144]}<image>Thought: Type \"usb-b\" in the search bar to find the product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-b\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: The task to add usb-b to the cart on Newegg is complete, indicating success in my actions.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12026873749749305645_1.png",
"training_data/AITW/aitw_images/webshopping/12026873749749305645_2.png",
"training_data/AITW/aitw_images/webshopping/12026873749749305645_3.png"
] | 7,493
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the smartphone's main screen where I can access the browser for Walmart.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_0.png"
] | 7,494
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to return to the smartphone's main screen where I can access the browser for Walmart.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ASSISTANT icon to open the search functionality for finding products on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 1359]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_0.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_1.png"
] | 7,495
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to return to the smartphone's main screen where I can access the browser for Walmart.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the ASSISTANT icon to open the search functionality for finding products on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 1359]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Walmart entry to access the website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 304]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_0.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_1.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_2.png"
] | 7,496
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the ASSISTANT icon to open the search functionality for finding products on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 1359]}<image>Thought: Click on the Walmart entry to access the website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 304]}<image>",
"role": "user"
},
{
"content": "Thought: Click on walmart.com to access the Walmart website and start the search for \"sony triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 765]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_1.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_2.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_3.png"
] | 7,497
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Walmart entry to access the website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 304]}<image>Thought: Click on walmart.com to access the Walmart website and start the search for \"sony triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 765]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to initiate the product search for \"sony triple a\" on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_2.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_3.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_4.png"
] | 7,498
|
[
{
"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: Search for \"sony triple a\" on walmart.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on walmart.com to access the Walmart website and start the search for \"sony triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 765]}<image>Thought: Click the search bar to initiate the product search for \"sony triple a\" on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"sony triple A\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"sony triple A\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7203238972534325494_3.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_4.png",
"training_data/AITW/aitw_images/webshopping/7203238972534325494_5.png"
] | 7,499
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.