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: Add acer nitro to the cart on costco.com<image>Thought: Press home to return to the main screen and access the Costco app or website.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open your email app and check for links or promotions for Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [495, 1139]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_0.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_1.png"
] | 9,100
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Press home to return to the main screen and access the Costco app or website.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the ENVELOPE to open your email app and check for links or promotions for Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [495, 1139]}<image>",
"role": "user"
},
{
"content": "Thought: Click the cart link to view your shopping cart on the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 96]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_0.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_1.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_2.png"
] | 9,101
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the ENVELOPE to open your email app and check for links or promotions for Costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [495, 1139]}<image>Thought: Click the cart link to view your shopping cart on the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 96]}<image>",
"role": "user"
},
{
"content": "Thought: You want to visit the Costco website to find and add an Acer Nitro to your cart. Typing \"costco.com\" in the search bar allows you to navigate directly to the site.\nAction: {\"action\": \"TYPE\", \"value\": \"costco.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_1.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_2.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_3.png"
] | 9,102
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the cart link to view your shopping cart on the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 96]}<image>Thought: You want to visit the Costco website to find and add an Acer Nitro to your cart. Typing \"costco.com\" in the search bar allows you to navigate directly to the site.\nAction: {\"action\": \"TYPE\", \"value\": \"costco.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the link for costco.com to navigate to the website and start shopping for acer nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 297]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_2.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_3.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_4.png"
] | 9,103
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: You want to visit the Costco website to find and add an Acer Nitro to your cart. Typing \"costco.com\" in the search bar allows you to navigate directly to the site.\nAction: {\"action\": \"TYPE\", \"value\": \"costco.com\", \"position\": null}<image>Thought: Click the link for costco.com to navigate to the website and start shopping for acer nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 297]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco link from Google search results to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 526]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_3.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_4.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_5.png"
] | 9,104
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the link for costco.com to navigate to the website and start shopping for acer nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 297]}<image>Thought: Click on the Costco link from Google search results to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 526]}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to begin looking for the Acer Nitro on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 269]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_4.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_5.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_6.png"
] | 9,105
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click on the Costco link from Google search results to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 526]}<image>Thought: Click Search to begin looking for the Acer Nitro on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 269]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer nitro\" in the search bar to locate the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_5.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_6.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_7.png"
] | 9,106
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click Search to begin looking for the Acer Nitro on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 269]}<image>Thought: Type \"acer nitro\" in the search bar to locate the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 281]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_6.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_7.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_8.png"
] | 9,107
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Type \"acer nitro\" in the search bar to locate the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>Thought: Click the magnifying glass to initiate the search for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 281]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Acer Nitro IPS Gaming Monitor to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1146]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_7.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_8.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_9.png"
] | 9,108
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the magnifying glass to initiate the search for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 281]}<image>Thought: Click the Acer Nitro IPS Gaming Monitor to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1146]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more information about the Acer Nitro monitor and find the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_8.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_9.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_10.png"
] | 9,109
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the Acer Nitro IPS Gaming Monitor to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [459, 1146]}<image>Thought: Scroll down to view more information about the Acer Nitro monitor and find the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional options or buttons for adding the Acer Nitro monitor to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_9.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_10.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_11.png"
] | 9,110
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Scroll down to view more information about the Acer Nitro monitor and find the add-to-cart button.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view additional options or buttons for adding the Acer Nitro monitor to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to initiate the process of purchasing the Acer Nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 1102]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_10.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_11.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_12.png"
] | 9,111
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Scroll down to view additional options or buttons for adding the Acer Nitro monitor to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to initiate the process of purchasing the Acer Nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 1102]}<image>",
"role": "user"
},
{
"content": "Thought: Click the View Cart button to verify that the Acer Nitro monitor is successfully added to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 570]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_11.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_12.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_13.png"
] | 9,112
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 acer nitro to the cart on costco.com<image>Thought: Click the \"Add to Cart\" button to initiate the process of purchasing the Acer Nitro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 1102]}<image>Thought: Click the View Cart button to verify that the Acer Nitro monitor is successfully added to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 570]}<image>",
"role": "user"
},
{
"content": "Thought: You added the Acer Nitro monitor to your cart, confirming it is successfully included for purchase.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4629137636191414018_12.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_13.png",
"training_data/AITW/aitw_images/webshopping/4629137636191414018_14.png"
] | 9,113
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to access the target.com website and find the search bar for input.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_0.png"
] | 9,114
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to access the target.com website and find the search bar for input.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to open the browser for shopping on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 376]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_0.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_1.png"
] | 9,115
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to access the target.com website and find the search bar for input.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome icon to open the browser for shopping on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 376]}<image>",
"role": "user"
},
{
"content": "Thought: Click the target.com/cart link to view the shopping cart for items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_0.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_1.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_2.png"
] | 9,116
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Click the Chrome icon to open the browser for shopping on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 376]}<image>Thought: Click the target.com/cart link to view the shopping cart for items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}<image>",
"role": "user"
},
{
"content": "Thought: Type target.com in the address bar to navigate to the Target website.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_1.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_2.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_3.png"
] | 9,117
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Click the target.com/cart link to view the shopping cart for items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 74]}<image>Thought: Type target.com in the address bar to navigate to the Target website.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to load the homepage of target.com and proceed with searching for \"logitech g pro.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_2.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_3.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_4.png"
] | 9,118
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Type target.com in the address bar to navigate to the Target website.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>Thought: Press enter to load the homepage of target.com and proceed with searching for \"logitech g pro.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to view the items added to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 213]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_3.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_4.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_5.png"
] | 9,119
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Press enter to load the homepage of target.com and proceed with searching for \"logitech g pro.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the SHOPPING CART icon to view the items added to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 213]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PERSON icon to access your account for better management of your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 293]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_4.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_5.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_6.png"
] | 9,120
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART icon to view the items added to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 213]}<image>Thought: Click the PERSON icon to access your account for better management of your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 293]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g pro\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_5.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_6.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_7.png"
] | 9,121
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Click the PERSON icon to access your account for better management of your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 293]}<image>Thought: Type \"logitech g pro\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to confirm the search for \"logitech g pro\" in the search bar at the top.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_6.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_7.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_8.png"
] | 9,122
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on target.com. Search for \"logitech g pro\" on target.com, select the first entry, and add it to the cart.<image>Thought: Type \"logitech g pro\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}<image>Thought: Press enter to confirm the search for \"logitech g pro\" in the search bar at the top.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the first entry for \"logitech g pro\" was successfully added to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/18420743916744138376_7.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_8.png",
"training_data/AITW/aitw_images/webshopping/18420743916744138376_9.png"
] | 9,123
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR RECT to access the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 541]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_0.png"
] | 9,124
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>Thought: Click the NAV BAR RECT to access the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 541]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon\" to search for the Amazon app and access the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_0.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_1.png"
] | 9,125
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>Thought: Click the NAV BAR RECT to access the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 541]}<image>Thought: Type \"amazon\" to search for the Amazon app and access the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon to access the shopping platform where I can manage my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [105, 113]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_0.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_1.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_2.png"
] | 9,126
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>Thought: Type \"amazon\" to search for the Amazon app and access the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon \", \"position\": null}<image>Thought: Click on Amazon to access the shopping platform where I can manage my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [105, 113]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"amazon\" link to access the Amazon website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_1.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_2.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_3.png"
] | 9,127
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>Thought: Click on Amazon to access the shopping platform where I can manage my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [105, 113]}<image>Thought: Click on the \"amazon\" link to access the Amazon website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Shop Amazon Basics\" to access products for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 499]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_2.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_3.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_4.png"
] | 9,128
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Add logitech g pro to the cart on amazon<image>Thought: Click on the \"amazon\" link to access the Amazon website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 73]}<image>Thought: Click on \"Shop Amazon Basics\" to access products for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 499]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task by successfully adding the Logitech G Pro to your shopping cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9159207824025451655_3.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_4.png",
"training_data/AITW/aitw_images/webshopping/9159207824025451655_5.png"
] | 9,129
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>",
"role": "user"
},
{
"content": "Thought: Close the error message to proceed with your search for a 4K TV on Best Buy without interruption.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 335]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_0.png"
] | 9,130
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Close the error message to proceed with your search for a 4K TV on Best Buy without interruption.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 335]}<image>",
"role": "user"
},
{
"content": "Thought: Click the GOOGLE icon to open the search engine to look for a 4k TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_0.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_1.png"
] | 9,131
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Close the error message to proceed with your search for a 4K TV on Best Buy without interruption.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 335]}<image>Thought: Click the GOOGLE icon to open the search engine to look for a 4k TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google icon to open the search application for finding a 4K TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_0.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_1.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_2.png"
] | 9,132
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click the GOOGLE icon to open the search engine to look for a 4k TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>Thought: Click on the Google icon to open the search application for finding a 4K TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google app to start searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_1.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_2.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_3.png"
] | 9,133
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click on the Google icon to open the search application for finding a 4K TV on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>Thought: Click on the Google app to start searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely wants to see more options for 4k TVs, so scrolling up helps bring other search results into view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_2.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_3.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_4.png"
] | 9,134
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click on the Google app to start searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 221]}<image>Thought: The user likely wants to see more options for 4k TVs, so scrolling up helps bring other search results into view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view more search results related to the query.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_3.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_4.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_5.png"
] | 9,135
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: The user likely wants to see more options for 4k TVs, so scrolling up helps bring other search results into view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view more search results related to the query.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search result for \"Living Room Chairs - Crate & Barrel\" to explore furniture options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 71]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_4.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_5.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_6.png"
] | 9,136
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Scroll up to view more search results related to the query.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on the search result for \"Living Room Chairs - Crate & Barrel\" to explore furniture options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 71]}<image>",
"role": "user"
},
{
"content": "Thought: You would click X to clear the previous search terms in the Google search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 33]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_5.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_6.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_7.png"
] | 9,137
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click on the search result for \"Living Room Chairs - Crate & Barrel\" to explore furniture options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 71]}<image>Thought: You would click X to clear the previous search terms in the Google search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 33]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Search bar to start entering a query for a 4K TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 22]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_6.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_7.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_8.png"
] | 9,138
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: You would click X to clear the previous search terms in the Google search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 33]}<image>Thought: Click on the Search bar to start entering a query for a 4K TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 22]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"4k TV on Best Buy\" in the search bar to initiate the search effectively.\nAction: {\"action\": \"TYPE\", \"value\": \" 4k TV on Best Buy \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_7.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_8.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_9.png"
] | 9,139
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click on the Search bar to start entering a query for a 4K TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 22]}<image>Thought: Type \"4k TV on Best Buy\" in the search bar to initiate the search effectively.\nAction: {\"action\": \"TYPE\", \"value\": \" 4k TV on Best Buy \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the suggestion \"4k tv best buy\" to refine the search for 4K TVs available at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [87, 66]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_8.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_9.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_10.png"
] | 9,140
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Type \"4k TV on Best Buy\" in the search bar to initiate the search effectively.\nAction: {\"action\": \"TYPE\", \"value\": \" 4k TV on Best Buy \", \"position\": null}<image>Thought: Click the suggestion \"4k tv best buy\" to refine the search for 4K TVs available at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [87, 66]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Shop Top\" to access the section specifically for 4K TVs at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 217]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_9.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_10.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_11.png"
] | 9,141
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click the suggestion \"4k tv best buy\" to refine the search for 4K TVs available at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [87, 66]}<image>Thought: Click on \"Shop Top\" to access the section specifically for 4K TVs at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 217]}<image>",
"role": "user"
},
{
"content": "Thought: Select United States to access the Best Buy website relevant for your location before searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 205]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_10.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_11.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_12.png"
] | 9,142
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Click on \"Shop Top\" to access the section specifically for 4K TVs at Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 217]}<image>Thought: Select United States to access the Best Buy website relevant for your location before searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 205]}<image>",
"role": "user"
},
{
"content": "Thought: Allow location access to enhance search results for nearby 4K TVs on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 332]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_11.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_12.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_13.png"
] | 9,143
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a 4k TV on Best Buy<image>Thought: Select United States to access the Best Buy website relevant for your location before searching for a 4k TV.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 205]}<image>Thought: Allow location access to enhance search results for nearby 4K TVs on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 332]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for 4k TVs on Best Buy, indicating that you found relevant results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15195828787994054789_12.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_13.png",
"training_data/AITW/aitw_images/webshopping/15195828787994054789_14.png"
] | 9,144
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 4k TVs on Best Buy.<image>",
"role": "user"
},
{
"content": "Thought: Click the Google app icon to start searching for 4k TVs on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 871]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/461024906824269477_0.png"
] | 9,145
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 4k TVs on Best Buy.<image>Thought: Click the Google app icon to start searching for 4k TVs on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 871]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome browser icon to open it for searching 4k TVs on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [467, 921]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/461024906824269477_0.png",
"training_data/AITW/aitw_images/webshopping/461024906824269477_1.png"
] | 9,146
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 4k TVs on Best Buy.<image>Thought: Click the Google app icon to start searching for 4k TVs on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 871]}<image>Thought: Click the Chrome browser icon to open it for searching 4k TVs on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [467, 921]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully completed the task of searching for 4k TVs on Best Buy.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/461024906824269477_0.png",
"training_data/AITW/aitw_images/webshopping/461024906824269477_1.png",
"training_data/AITW/aitw_images/webshopping/461024906824269477_2.png"
] | 9,147
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current email setup screen and return to the main menu.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_0.png"
] | 9,148
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Press home to exit the current email setup screen and return to the main menu.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MIC to enable voice input for easier searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 909]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_0.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_1.png"
] | 9,149
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Press home to exit the current email setup screen and return to the main menu.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the MIC to enable voice input for easier searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 909]}<image>",
"role": "user"
},
{
"content": "Thought: You click the upward arrow to view more options in the shopping cart interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 80]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_0.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_1.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_2.png"
] | 9,150
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Click the MIC to enable voice input for easier searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 909]}<image>Thought: You click the upward arrow to view more options in the shopping cart interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 80]}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue spot on \"Subtotal $1969\" to view the shopping cart details on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 704]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_1.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_2.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_3.png"
] | 9,151
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: You click the upward arrow to view more options in the shopping cart interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 80]}<image>Thought: Click the blue spot on \"Subtotal $1969\" to view the shopping cart details on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 704]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Sign in\" to access your Amazon account and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 219]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_2.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_3.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_4.png"
] | 9,152
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Click the blue spot on \"Subtotal $1969\" to view the shopping cart details on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 704]}<image>Thought: Click \"Sign in\" to access your Amazon account and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 219]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"usb-c to usb-a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-c to usb-a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_3.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_4.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_5.png"
] | 9,153
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Click \"Sign in\" to access your Amazon account and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 219]}<image>Thought: Type \"usb-c to usb-a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-c to usb-a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"usb-a\" to select the desired product from the search suggestions in the Amazon search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 263]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_4.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_5.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_6.png"
] | 9,154
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Type \"usb-c to usb-a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-c to usb-a\", \"position\": null}<image>Thought: Click on \"usb-a\" to select the desired product from the search suggestions in the Amazon search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 263]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Female Adapter\" to view details about this USB-C to USB-A product before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 530]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_5.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_6.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_7.png"
] | 9,155
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Click on \"usb-a\" to select the desired product from the search suggestions in the Amazon search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 263]}<image>Thought: Click the \"Female Adapter\" to view details about this USB-C to USB-A product before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 530]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results and locate the \"usb-c to usb-a\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_6.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_7.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_8.png"
] | 9,156
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Click the \"Female Adapter\" to view details about this USB-C to USB-A product before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 530]}<image>Thought: Scroll down to view more results and locate the \"usb-c to usb-a\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate the \"Add to Cart\" button for the USB-C to USB-A adapter.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_7.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_8.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_9.png"
] | 9,157
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Scroll down to view more results and locate the \"usb-c to usb-a\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to locate the \"Add to Cart\" button for the USB-C to USB-A adapter.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include \"usb-c to usb-a\" in the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 689]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_8.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_9.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_10.png"
] | 9,158
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon. Add \"usb-c to usb-a\" to the cart on amazon<image>Thought: Scroll down to locate the \"Add to Cart\" button for the USB-C to USB-A adapter.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to include \"usb-c to usb-a\" in the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 689]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully added \"usb-c to usb-a\" to the cart since you see it in the shopping cart with a subtotal displayed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5984484126912864426_9.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_10.png",
"training_data/AITW/aitw_images/webshopping/5984484126912864426_11.png"
] | 9,159
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome icon to open the browser and access eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 865]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_0.png"
] | 9,160
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the Chrome icon to open the browser and access eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 865]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the browser icon to open it for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 856]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_0.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_1.png"
] | 9,161
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the Chrome icon to open the browser and access eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 865]}<image>Thought: Click on the browser icon to open it for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 856]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the browser icon to open the web browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 853]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_0.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_1.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_2.png"
] | 9,162
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the browser icon to open it for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 856]}<image>Thought: Click on the browser icon to open the web browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 853]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"New tab\" option in the browser menu to start searching eBay for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 849]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_1.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_2.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_3.png"
] | 9,163
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the browser icon to open the web browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 853]}<image>Thought: Click on the \"New tab\" option in the browser menu to start searching eBay for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 849]}<image>",
"role": "user"
},
{
"content": "Thought: Click the browser icon to open it and start your eBay search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 853]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_2.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_3.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_4.png"
] | 9,164
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the \"New tab\" option in the browser menu to start searching eBay for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 849]}<image>Thought: Click the browser icon to open it and start your eBay search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 853]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 132]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_3.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_4.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_5.png"
] | 9,165
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the browser icon to open it and start your eBay search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 853]}<image>Thought: Click the magnifying glass to access the search function on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 132]}<image>",
"role": "user"
},
{
"content": "Thought: You enter \"amazon basics triple a\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_4.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_5.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_6.png"
] | 9,166
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to access the search function on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [292, 132]}<image>Thought: You enter \"amazon basics triple a\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"amazon basics triple a\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_5.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_6.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_7.png"
] | 9,167
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: You enter \"amazon basics triple a\" in the search bar to find the desired product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}<image>Thought: Press enter to initiate the search for \"amazon basics triple a\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the first entry to view details and add the item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 556]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_6.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_7.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_8.png"
] | 9,168
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Press enter to initiate the search for \"amazon basics triple a\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on the first entry to view details and add the item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 556]}<image>",
"role": "user"
},
{
"content": "Thought: Click the item pack to access additional options for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [518, 578]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_7.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_8.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_9.png"
] | 9,169
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the first entry to view details and add the item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 556]}<image>Thought: Click the item pack to access additional options for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [518, 578]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the item to view details and ensure it's the correct product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [450, 553]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_8.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_9.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_10.png"
] | 9,170
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the item pack to access additional options for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [518, 578]}<image>Thought: Click on the item to view details and ensure it's the correct product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [450, 553]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional product details and images of the Amazon Basics AAA batteries.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_9.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_10.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_11.png"
] | 9,171
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the item to view details and ensure it's the correct product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [450, 553]}<image>Thought: Scroll down to view additional product details and images of the Amazon Basics AAA batteries.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the Amazon Basics AAA batteries in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 573]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_10.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_11.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_12.png"
] | 9,172
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view additional product details and images of the Amazon Basics AAA batteries.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the Amazon Basics AAA batteries in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 573]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"View in cart\" button to access the current items in the shopping cart for review.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 575]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_11.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_12.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_13.png"
] | 9,173
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click \"Add to cart\" to include the Amazon Basics AAA batteries in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 573]}<image>Thought: Click the \"View in cart\" button to access the current items in the shopping cart for review.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 575]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view all items in the cart and locate the \"Remove\" option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_12.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_13.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_14.png"
] | 9,174
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"View in cart\" button to access the current items in the shopping cart for review.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 575]}<image>Thought: Scroll down to view all items in the cart and locate the \"Remove\" option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [481, 597]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_13.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_14.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_15.png"
] | 9,175
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on ebay. Search for amazon basics triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view all items in the cart and locate the \"Remove\" option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click Remove to delete the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [481, 597]}<image>",
"role": "user"
},
{
"content": "Thought: You need to clear your cart before adding a new item. The cart shows the existing item that needs removal. You confirm that the current task of clearing the cart is complete, allowing you to proceed with adding a new item.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1093960121053253196_14.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_15.png",
"training_data/AITW/aitw_images/webshopping/1093960121053253196_16.png"
] | 9,176
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: This screen shows the email setup options, indicating you're in a different app. Press home to access the main screen and launch the browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_0.png"
] | 9,177
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: This screen shows the email setup options, indicating you're in a different app. Press home to access the main screen and launch the browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Access the chat feature to seek assistance with clearing the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 1301]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_0.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_1.png"
] | 9,178
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: This screen shows the email setup options, indicating you're in a different app. Press home to access the main screen and launch the browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Access the chat feature to seek assistance with clearing the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 1301]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bestbuy\" in the search bar to initiate a search for the Best Buy website.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_0.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_1.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_2.png"
] | 9,179
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Access the chat feature to seek assistance with clearing the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 1301]}<image>Thought: Type \"bestbuy\" in the search bar to initiate a search for the Best Buy website.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Best Buy to navigate to the official Best Buy website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 179]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_1.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_2.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_3.png"
] | 9,180
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Type \"bestbuy\" in the search bar to initiate a search for the Best Buy website.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>Thought: Click Best Buy to navigate to the official Best Buy website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 179]}<image>",
"role": "user"
},
{
"content": "Thought: Navigate to the Best Buy website by clicking on the first entry in search results. Search for \"apple airpods pro\" using the site's search bar. Select the first entry in the search results for apple airpods pro to view product details. Click \"Buy\" to add the item to your shopping cart and proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 514]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_2.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_3.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_4.png"
] | 9,181
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click Best Buy to navigate to the official Best Buy website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 179]}<image>Thought: Navigate to the Best Buy website by clicking on the first entry in search results. Search for \"apple airpods pro\" using the site's search bar. Select the first entry in the search results for apple airpods pro to view product details. Click \"Buy\" to add the item to your shopping cart and proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 514]}<image>",
"role": "user"
},
{
"content": "Thought: Click Allow to grant location access for a better shopping experience on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 810]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_3.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_4.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_5.png"
] | 9,182
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Navigate to the Best Buy website by clicking on the first entry in search results. Search for \"apple airpods pro\" using the site's search bar. Select the first entry in the search results for apple airpods pro to view product details. Click \"Buy\" to add the item to your shopping cart and proceed with your purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 514]}<image>Thought: Click Allow to grant location access for a better shopping experience on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 810]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to view items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 250]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_4.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_5.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_6.png"
] | 9,183
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click Allow to grant location access for a better shopping experience on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 810]}<image>Thought: Click the SHOPPING CART to view items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 250]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Deals\" to explore available offers and promotions on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 255]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_5.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_6.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_7.png"
] | 9,184
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART to view items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 250]}<image>Thought: Click \"Deals\" to explore available offers and promotions on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 255]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods pro\" in the search bar at the top of the screen to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_6.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_7.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_8.png"
] | 9,185
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click \"Deals\" to explore available offers and promotions on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 255]}<image>Thought: Type \"apple airpods pro\" in the search bar at the top of the screen to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"apple airpods pro\" entry to view further details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 260]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_7.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_8.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_9.png"
] | 9,186
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Type \"apple airpods pro\" in the search bar at the top of the screen to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}<image>Thought: Click on the \"apple airpods pro\" entry to view further details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 260]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the Apple AirPods Pro in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [529, 898]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_8.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_9.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_10.png"
] | 9,187
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on the \"apple airpods pro\" entry to view further details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 260]}<image>Thought: Click \"Add to Cart\" to include the Apple AirPods Pro in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [529, 898]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to add the selected item, Apple AirPods Pro, to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [536, 984]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_9.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_10.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_11.png"
] | 9,188
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for apple airpods pro on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click \"Add to Cart\" to include the Apple AirPods Pro in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [529, 898]}<image>Thought: Click the \"Add to Cart\" button to add the selected item, Apple AirPods Pro, to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [536, 984]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the user successfully added the Apple AirPods Pro to their cart on BestBuy.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12148118602229154082_10.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_11.png",
"training_data/AITW/aitw_images/webshopping/12148118602229154082_12.png"
] | 9,189
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google app to start the search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 535]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_0.png"
] | 9,190
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click on the Google app to start the search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 535]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for products on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 140]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_0.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_1.png"
] | 9,191
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click on the Google app to start the search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 535]}<image>Thought: Click the magnifying glass to access the search function for products on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 140]}<image>",
"role": "user"
},
{
"content": "Thought: Click X to clear the previous search so I can input \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 143]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_0.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_1.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_2.png"
] | 9,192
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to access the search function for products on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 140]}<image>Thought: Click X to clear the previous search so I can input \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 143]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_1.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_2.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_3.png"
] | 9,193
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click X to clear the previous search so I can input \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 143]}<image>Thought: Type \"apple airpods\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate a search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 141]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_2.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_3.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_4.png"
] | 9,194
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Type \"apple airpods\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>Thought: Click the Search bar to initiate a search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 141]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods\" into the search bar to initiate the search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_3.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_4.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_5.png"
] | 9,195
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click the Search bar to initiate a search for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 141]}<image>Thought: Type \"apple airpods\" into the search bar to initiate the search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"apple airpods\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 215]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_4.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_5.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_6.png"
] | 9,196
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Type \"apple airpods\" into the search bar to initiate the search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>Thought: Click on \"apple airpods\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 215]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"apple airpods\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_5.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_6.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_7.png"
] | 9,197
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click on \"apple airpods\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [86, 215]}<image>Thought: Scroll down to view more search results for \"apple airpods\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to select the first entry for Apple AirPods as it's the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 542]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_6.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_7.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_8.png"
] | 9,198
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"apple airpods\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to select the first entry for Apple AirPods as it's the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 542]}<image>",
"role": "user"
},
{
"content": "Thought: You would click \"Add to cart\" to finalize adding the Apple AirPods after selecting them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 539]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_7.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_8.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_9.png"
] | 9,199
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.