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: Open Chrome app and search bestbuy.com in chrome search bar<image>Thought: Click the Chrome icon to launch the app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 913]}<image>Thought: You mistakenly clicked the link to Costco's catalog instead of opening the Chrome app. You need to return to your home screen or re-open Chrome.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [230, 85]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bestbuy.com\" in the Chrome search bar to initiate a web search for the site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_0.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_1.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_2.png"
] | 5,100
|
[
{
"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: Open Chrome app and search bestbuy.com in chrome search bar<image>Thought: You mistakenly clicked the link to Costco's catalog instead of opening the Chrome app. You need to return to your home screen or re-open Chrome.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [230, 85]}<image>Thought: Type \"bestbuy.com\" in the Chrome search bar to initiate a web search for the site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue link for bestbuy.com as it's the correct website you want to open.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 253]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_1.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_2.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_3.png"
] | 5,101
|
[
{
"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: Open Chrome app and search bestbuy.com in chrome search bar<image>Thought: Type \"bestbuy.com\" in the Chrome search bar to initiate a web search for the site.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy.com\", \"position\": null}<image>Thought: Click the blue link for bestbuy.com as it's the correct website you want to open.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 253]}<image>",
"role": "user"
},
{
"content": "Thought: You have opened the Chrome app, evidenced by the search bar visible at the top. You successfully searched for bestbuy.com, as shown in the search results. The status indicates that your task is complete since you intended to find Best Buy’s website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_2.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_3.png",
"training_data/AITW/aitw_images/single/2342604083756439960.138-402.Open Chrome app and search bestbuy.com in chrome search bar_4.png"
] | 5,102
|
[
{
"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: go to Costco Search bar and type razer blade <image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to access it for typing. This allows you to input \"razer blade\" as a search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 288]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _0.png"
] | 5,103
|
[
{
"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: go to Costco Search bar and type razer blade <image>Thought: Click the Search bar to access it for typing. This allows you to input \"razer blade\" as a search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 288]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the Costco search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _0.png",
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _1.png"
] | 5,104
|
[
{
"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: go to Costco Search bar and type razer blade <image>Thought: Click the Search bar to access it for typing. This allows you to input \"razer blade\" as a search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 288]}<image>Thought: Type \"razer blade\" in the Costco search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Select the Costco search bar and type \"razer blade\" to find the desired product. The operation is marked as complete since relevant suggestions are displayed below.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _0.png",
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _1.png",
"training_data/AITW/aitw_images/single/16624095375522749591.191-220.go to Costco Search bar and type razer blade _2.png"
] | 5,105
|
[
{
"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: enter in the walmart.com search bar: acer predator<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer predator\" in the Walmart search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_0.png"
] | 5,106
|
[
{
"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: enter in the walmart.com search bar: acer predator<image>Thought: Type \"acer predator\" in the Walmart search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"predator\" in the suggested search bar options to quickly select a relevant query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 357]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_0.png",
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_1.png"
] | 5,107
|
[
{
"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: enter in the walmart.com search bar: acer predator<image>Thought: Type \"acer predator\" in the Walmart search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: Click on \"predator\" in the suggested search bar options to quickly select a relevant query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 357]}<image>",
"role": "user"
},
{
"content": "Thought: You accepted the entered text \"acer predator\" into the search bar for Walmart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_0.png",
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_1.png",
"training_data/AITW/aitw_images/single/8044239873197660914.218-277.enter in the walmart.com search bar: acer predator_2.png"
] | 5,108
|
[
{
"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: Go to the first result of macbook pro 13 inch in ebay.com and then add to cart<image>",
"role": "user"
},
{
"content": "Thought: Click on the Warranty option to view details about product protection and additional services.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 529]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_0.png"
] | 5,109
|
[
{
"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: Go to the first result of macbook pro 13 inch in ebay.com and then add to cart<image>Thought: Click on the Warranty option to view details about product protection and additional services.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 529]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the first result for the MacBook Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_0.png",
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_1.png"
] | 5,110
|
[
{
"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: Go to the first result of macbook pro 13 inch in ebay.com and then add to cart<image>Thought: Click on the Warranty option to view details about product protection and additional services.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 529]}<image>Thought: Scroll down to view more details about the first result for the MacBook Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to store the first MacBook Pro result for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 698]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_0.png",
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_1.png",
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_2.png"
] | 5,111
|
[
{
"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: Go to the first result of macbook pro 13 inch in ebay.com and then add to cart<image>Thought: Scroll down to view more details about the first result for the MacBook Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to store the first MacBook Pro result for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 698]}<image>",
"role": "user"
},
{
"content": "Thought: You scrolled to find the MacBook Pro listing, then successfully added it to your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_1.png",
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_2.png",
"training_data/AITW/aitw_images/single/12763048216478746152.780-877.Go to the first result of macbook pro 13 inch in ebay.com and then add to cart_3.png"
] | 5,112
|
[
{
"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: go to the search bar and search for newegg<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input your query. You need to search for Newegg, so locating the search bar is essential.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [221, 296]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_0.png"
] | 5,113
|
[
{
"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: go to the search bar and search for newegg<image>Thought: Click the search bar to input your query. You need to search for Newegg, so locating the search bar is essential.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [221, 296]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg\" in the search bar to initiate a web address search for that site.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_0.png",
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_1.png"
] | 5,114
|
[
{
"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: go to the search bar and search for newegg<image>Thought: Click the search bar to input your query. You need to search for Newegg, so locating the search bar is essential.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [221, 296]}<image>Thought: Type \"newegg\" in the search bar to initiate a web address search for that site.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the suggestion for negg.com in the search bar to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 202]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_0.png",
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_1.png",
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_2.png"
] | 5,115
|
[
{
"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: go to the search bar and search for newegg<image>Thought: Type \"newegg\" in the search bar to initiate a web address search for that site.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>Thought: Click on the suggestion for negg.com in the search bar to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 202]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely typed \"newegg\" in the search bar to find specific products or information about Newegg. The successful completion status confirms that the search was executed as intended.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_1.png",
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_2.png",
"training_data/AITW/aitw_images/single/16910333049710525873.194-318.go to the search bar and search for newegg_3.png"
] | 5,116
|
[
{
"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: Go to cart in ebay<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access items I've added for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [218, 80]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6957599455531972592.298-426.Go to cart in ebay_0.png"
] | 5,117
|
[
{
"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: Go to cart in ebay<image>Thought: Click SHOPPING CART to access items I've added for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [218, 80]}<image>",
"role": "user"
},
{
"content": "Thought: You confirmed that you successfully navigated to the cart by checking the visible shopping cart interface.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6957599455531972592.298-426.Go to cart in ebay_0.png",
"training_data/AITW/aitw_images/single/6957599455531972592.298-426.Go to cart in ebay_1.png"
] | 5,118
|
[
{
"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: Search bose soundlink on Costco <image>",
"role": "user"
},
{
"content": "Thought: Type \"bose soundlink\" in the search bar to find specific products at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _0.png"
] | 5,119
|
[
{
"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: Search bose soundlink on Costco <image>Thought: Type \"bose soundlink\" in the search bar to find specific products at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass icon to start a search for \"bose soundlink.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [657, 264]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _0.png",
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _1.png"
] | 5,120
|
[
{
"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: Search bose soundlink on Costco <image>Thought: Type \"bose soundlink\" in the search bar to find specific products at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>Thought: Click the magnifying glass icon to start a search for \"bose soundlink.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [657, 264]}<image>",
"role": "user"
},
{
"content": "Thought: The search for \"bose soundlink\" on the Costco website is successful; now review the displayed results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _0.png",
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _1.png",
"training_data/AITW/aitw_images/single/9005571901941304035.240-313.Search bose soundlink on Costco _2.png"
] | 5,121
|
[
{
"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: Checkout the searched result<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results related to \"newegg.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_0.png"
] | 5,122
|
[
{
"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: Checkout the searched result<image>Thought: Scroll down to view more results related to \"newegg.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options and details related to the searched result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_0.png",
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_1.png"
] | 5,123
|
[
{
"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: Checkout the searched result<image>Thought: Scroll down to view more results related to \"newegg.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options and details related to the searched result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully completed checking the searched result on the Newegg website in the Google search.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_0.png",
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_1.png",
"training_data/AITW/aitw_images/single/16568651445420613939.385-442.Checkout the searched result_2.png"
] | 5,124
|
[
{
"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: Show the shopping cart on costco.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the Cart icon to access the shopping cart details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 151]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/14383944572065501388.185-275.Show the shopping cart on costco.com_0.png"
] | 5,125
|
[
{
"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: Show the shopping cart on costco.com<image>Thought: Click on the Cart icon to access the shopping cart details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 151]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully accessed the shopping cart page on Costco.com as indicated by the completion status.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/14383944572065501388.185-275.Show the shopping cart on costco.com_0.png",
"training_data/AITW/aitw_images/single/14383944572065501388.185-275.Show the shopping cart on costco.com_1.png"
] | 5,126
|
[
{
"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: go to newegg cart and go back to previous page <image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access your cart on Newegg. Press back to return to the previous page after viewing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [582, 196]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _0.png"
] | 5,127
|
[
{
"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: go to newegg cart and go back to previous page <image>Thought: Click the SHOPPING CART icon to access your cart on Newegg. Press back to return to the previous page after viewing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [582, 196]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return from the empty cart page to the previous shopping page.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _0.png",
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _1.png"
] | 5,128
|
[
{
"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: go to newegg cart and go back to previous page <image>Thought: Click the SHOPPING CART icon to access your cart on Newegg. Press back to return to the previous page after viewing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [582, 196]}<image>Thought: Press back to return from the empty cart page to the previous shopping page.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Open the Newegg website to access the cart. Click on the cart icon in the upper right corner to view items. After reviewing, press back to return to the previous page from the cart. Confirm task completion after returning successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _0.png",
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _1.png",
"training_data/AITW/aitw_images/single/17357248874076582134.576-632.go to newegg cart and go back to previous page _2.png"
] | 5,129
|
[
{
"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: Go to costco search bar <image>",
"role": "user"
},
{
"content": "Thought: Click on the Search bar to access the search function and input desired query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [233, 276]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8414123138211107600.160-228.Go to costco search bar _0.png"
] | 5,130
|
[
{
"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: Go to costco search bar <image>Thought: Click on the Search bar to access the search function and input desired query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [233, 276]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully navigated to the Costco search bar, indicating they can now begin searching for items.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8414123138211107600.160-228.Go to costco search bar _0.png",
"training_data/AITW/aitw_images/single/8414123138211107600.160-228.Go to costco search bar _1.png"
] | 5,131
|
[
{
"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 target.com in google search bar<image>",
"role": "user"
},
{
"content": "Thought: Type \"target.com\" in the Google search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" target.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_0.png"
] | 5,132
|
[
{
"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 target.com in google search bar<image>Thought: Type \"target.com\" in the Google search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" target.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin entering the website URL.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 80]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_0.png",
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_1.png"
] | 5,133
|
[
{
"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 target.com in google search bar<image>Thought: Type \"target.com\" in the Google search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" target.com\", \"position\": null}<image>Thought: Click the search bar to begin entering the website URL.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 80]}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for target.com in the Google search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_0.png",
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_1.png",
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_2.png"
] | 5,134
|
[
{
"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 target.com in google search bar<image>Thought: Click the search bar to begin entering the website URL.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 80]}<image>Thought: Press enter to execute the search for target.com in the Google search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You searched for target.com in the Google search bar, confirming successful navigation to the desired website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_1.png",
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_2.png",
"training_data/AITW/aitw_images/single/17333479265158694713.120-212.search for target.com in google search bar_3.png"
] | 5,135
|
[
{
"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: close Current page and go to Target Search bar then type panasonic triple a <image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the current page indicating you're done with that item not in stock. After closing, navigate to the Target search bar for a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 213]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _0.png"
] | 5,136
|
[
{
"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: close Current page and go to Target Search bar then type panasonic triple a <image>Thought: Click the X to close the current page indicating you're done with that item not in stock. After closing, navigate to the Target search bar for a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 213]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to open the search bar since it is necessary for typing the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _0.png",
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _1.png"
] | 5,137
|
[
{
"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: close Current page and go to Target Search bar then type panasonic triple a <image>Thought: Click the X to close the current page indicating you're done with that item not in stock. After closing, navigate to the Target search bar for a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 213]}<image>Thought: Click the magnifying glass to open the search bar since it is necessary for typing the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 199]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"panasonic triple a\" in the Target Search bar to find the desired product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"panasonic triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _0.png",
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _1.png",
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _2.png"
] | 5,138
|
[
{
"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: close Current page and go to Target Search bar then type panasonic triple a <image>Thought: Click the magnifying glass to open the search bar since it is necessary for typing the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [443, 199]}<image>Thought: Type \"panasonic triple a\" in the Target Search bar to find the desired product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"panasonic triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You successfully closed the current page and accessed the Target search bar. You typed \"panasonic triple a\" into the search bar to find related products.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _1.png",
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _2.png",
"training_data/AITW/aitw_images/single/5732180867375747853.119-246.close Current page and go to Target Search bar then type panasonic triple a _3.png"
] | 5,139
|
[
{
"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: Go to the search bar<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to prepare for entering a query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 102]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5492278795149393035.70-144.Go to the search bar_0.png"
] | 5,140
|
[
{
"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: Go to the search bar<image>Thought: Click the search bar to prepare for entering a query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 102]}<image>",
"role": "user"
},
{
"content": "Thought: You would have focused on the search bar at the top to initiate a search.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5492278795149393035.70-144.Go to the search bar_0.png",
"training_data/AITW/aitw_images/single/5492278795149393035.70-144.Go to the search bar_1.png"
] | 5,141
|
[
{
"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: Go to google search bar.<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed the Google search bar at the top of the interface.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3003168337415958737.277-277.Go to google search bar._0.png"
] | 5,142
|
[
{
"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: open the first search result <image>",
"role": "user"
},
{
"content": "Thought: Click on the search result for \"i7 3.40GHz Retina - Big Sur - 3 Year\" to open the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [314, 543]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _0.png"
] | 5,143
|
[
{
"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: open the first search result <image>Thought: Click on the search result for \"i7 3.40GHz Retina - Big Sur - 3 Year\" to open the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [314, 543]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details of the first search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _0.png",
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _1.png"
] | 5,144
|
[
{
"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: open the first search result <image>Thought: Click on the search result for \"i7 3.40GHz Retina - Big Sur - 3 Year\" to open the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [314, 543]}<image>Thought: Scroll down to view more details of the first search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: The user likely clicked on the first search result to view detailed information about the product listed. The operation completed successfully, indicating they accessed the item's page effectively.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _0.png",
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _1.png",
"training_data/AITW/aitw_images/single/8706038447256911233.1161-1211.open the first search result _2.png"
] | 5,145
|
[
{
"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: Open first product from search result then add to cart<image>",
"role": "user"
},
{
"content": "Thought: Click on the product named \"Belt-KV-CL-ZEB-3\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 1079]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_0.png"
] | 5,146
|
[
{
"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: Open first product from search result then add to cart<image>Thought: Click on the product named \"Belt-KV-CL-ZEB-3\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 1079]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the first product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_0.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_1.png"
] | 5,147
|
[
{
"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: Open first product from search result then add to cart<image>Thought: Click on the product named \"Belt-KV-CL-ZEB-3\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 1079]}<image>Thought: Scroll down to view the first product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the details of the first product from the search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_0.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_1.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_2.png"
] | 5,148
|
[
{
"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: Open first product from search result then add to cart<image>Thought: Scroll down to view the first product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the details of the first product from the search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view product details and options for the first search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_1.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_2.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_3.png"
] | 5,149
|
[
{
"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: Open first product from search result then add to cart<image>Thought: Scroll down to view the details of the first product from the search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view product details and options for the first search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to proceed with purchasing the selected product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [325, 984]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_2.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_3.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_4.png"
] | 5,150
|
[
{
"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: Open first product from search result then add to cart<image>Thought: Scroll down to view product details and options for the first search result.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to proceed with purchasing the selected product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [325, 984]}<image>",
"role": "user"
},
{
"content": "Thought: Assume the first product was successfully opened and added to the cart. The task is now complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_3.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_4.png",
"training_data/AITW/aitw_images/single/11955553967274330393.796-936.Open first product from search result then add to cart_5.png"
] | 5,151
|
[
{
"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: Add to Cart the first result of paper towels<image>",
"role": "user"
},
{
"content": "Thought: Click Add to cart to select the first result for paper towels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [573, 1342]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/18431664730124659947.507-523.Add to Cart the first result of paper towels_0.png"
] | 5,152
|
[
{
"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: Add to Cart the first result of paper towels<image>Thought: Click Add to cart to select the first result for paper towels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [573, 1342]}<image>",
"role": "user"
},
{
"content": "Thought: You selected the first result for paper towels, indicating you wanted to purchase this item. You likely tapped on the \"Add to Cart\" button associated with the product. After successfully adding it to your cart, you marked the task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/18431664730124659947.507-523.Add to Cart the first result of paper towels_0.png",
"training_data/AITW/aitw_images/single/18431664730124659947.507-523.Add to Cart the first result of paper towels_1.png"
] | 5,153
|
[
{
"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: open second product from search results then add to cart and view in cart<image>",
"role": "user"
},
{
"content": "Thought: Click the second product titled \"Apple AirPods Pro with Mag Safe Wireless White Charging Case Music Running Kid\" to view its details. Then add the item to cart for purchase. Finally, access the cart to review selected items and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 734]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_0.png"
] | 5,154
|
[
{
"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: open second product from search results then add to cart and view in cart<image>Thought: Click the second product titled \"Apple AirPods Pro with Mag Safe Wireless White Charging Case Music Running Kid\" to view its details. Then add the item to cart for purchase. Finally, access the cart to review selected items and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 734]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the second product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_0.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_1.png"
] | 5,155
|
[
{
"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: open second product from search results then add to cart and view in cart<image>Thought: Click the second product titled \"Apple AirPods Pro with Mag Safe Wireless White Charging Case Music Running Kid\" to view its details. Then add the item to cart for purchase. Finally, access the cart to review selected items and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 734]}<image>Thought: Scroll down to view the second product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to save the product for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 708]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_0.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_1.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_2.png"
] | 5,156
|
[
{
"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: open second product from search results then add to cart and view in cart<image>Thought: Scroll down to view the second product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to save the product for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 708]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"View in cart\" button to access the cart and view added items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 697]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_1.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_2.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_3.png"
] | 5,157
|
[
{
"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: open second product from search results then add to cart and view in cart<image>Thought: Click the \"Add to cart\" button to save the product for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 708]}<image>Thought: Click the \"View in cart\" button to access the cart and view added items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 697]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully opened the second product from search results and added it to the cart. You viewed your items in the shopping cart to confirm everything was there.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_2.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_3.png",
"training_data/AITW/aitw_images/single/667669866302657337.591-833.open second product from search results then add to cart and view in cart_4.png"
] | 5,158
|
[
{
"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: search for macbook air on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Select the Amazon Basics option to explore its products related to MacBook Air.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 214]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_0.png"
] | 5,159
|
[
{
"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: search for macbook air on amazon.com<image>Thought: Select the Amazon Basics option to explore its products related to MacBook Air.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 214]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook air\" in the search bar to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_0.png",
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_1.png"
] | 5,160
|
[
{
"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: search for macbook air on amazon.com<image>Thought: Select the Amazon Basics option to explore its products related to MacBook Air.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 214]}<image>Thought: Type \"macbook air\" in the search bar to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"macbook air\" to select the item from the search suggestion list for detailed information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [53, 247]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_0.png",
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_1.png",
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_2.png"
] | 5,161
|
[
{
"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: search for macbook air on amazon.com<image>Thought: Type \"macbook air\" in the search bar to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}<image>Thought: Click on \"macbook air\" to select the item from the search suggestion list for detailed information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [53, 247]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully searched for \"macbook air\" by entering the query into the search bar on Amazon, resulting in a list of relevant products.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_1.png",
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_2.png",
"training_data/AITW/aitw_images/single/2391657864818287306.377-495.search for macbook air on amazon.com_3.png"
] | 5,162
|
[
{
"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: add the first product to cart<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to add the JBL Charge5 speaker to your cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 888]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10297730140680016070.942-984.add the first product to cart_0.png"
] | 5,163
|
[
{
"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: add the first product to cart<image>Thought: Click the \"Add to Cart\" button to add the JBL Charge5 speaker to your cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 888]}<image>",
"role": "user"
},
{
"content": "Thought: The user sees the \"Added to cart\" confirmation notice and recognizes that the product is now in their cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10297730140680016070.942-984.add the first product to cart_0.png",
"training_data/AITW/aitw_images/single/10297730140680016070.942-984.add the first product to cart_1.png"
] | 5,164
|
[
{
"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: go to amazon search bar and type razer blackwidow <image>",
"role": "user"
},
{
"content": "Thought: You click on \"Deliver to Netherlands\" to confirm your shipping location before searching for the item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 284]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _0.png"
] | 5,165
|
[
{
"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: go to amazon search bar and type razer blackwidow <image>Thought: You click on \"Deliver to Netherlands\" to confirm your shipping location before searching for the item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 284]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blackwidow\" in the search Amazon bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blackwidow\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _0.png",
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _1.png"
] | 5,166
|
[
{
"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: go to amazon search bar and type razer blackwidow <image>Thought: You click on \"Deliver to Netherlands\" to confirm your shipping location before searching for the item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 284]}<image>Thought: Type \"razer blackwidow\" in the search Amazon bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blackwidow\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Access the Amazon search bar to input \"razer blackwidow.\" The operation shows that the text has been successfully entered, completing the task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _0.png",
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _1.png",
"training_data/AITW/aitw_images/single/4544254946906675503.403-508.go to amazon search bar and type razer blackwidow _2.png"
] | 5,167
|
[
{
"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: go to apple airpods <image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"apple airpods\" in the search bar at the top of the screen.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7384430946461055313.553-691.go to apple airpods _0.png"
] | 5,168
|
[
{
"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: go to apple airpods <image>Thought: Press enter to execute the search for \"apple airpods\" in the search bar at the top of the screen.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You successfully searched for \"apple airpods\" in the Target website search bar, indicating the task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7384430946461055313.553-691.go to apple airpods _0.png",
"training_data/AITW/aitw_images/single/7384430946461055313.553-691.go to apple airpods _1.png"
] | 5,169
|
[
{
"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: Open first option from search result<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"PLAY\" button to open the first search result and view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 474]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/152021486084027792.379-420.Open first option from search result_0.png"
] | 5,170
|
[
{
"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: Open first option from search result<image>Thought: Click on the \"PLAY\" button to open the first search result and view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 474]}<image>",
"role": "user"
},
{
"content": "Thought: You opened the first search result displayed on the Amazon results page for \"apple airpods.\"\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/152021486084027792.379-420.Open first option from search result_0.png",
"training_data/AITW/aitw_images/single/152021486084027792.379-420.Open first option from search result_1.png"
] | 5,171
|
[
{
"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: Open the second product from search result, then add the product to the cart<image>",
"role": "user"
},
{
"content": "Thought: Click on the second product, identified by the blue spot, to view its details and options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 1092]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_0.png"
] | 5,172
|
[
{
"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: Open the second product from search result, then add the product to the cart<image>Thought: Click on the second product, identified by the blue spot, to view its details and options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 1092]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the second product from the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_0.png",
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_1.png"
] | 5,173
|
[
{
"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: Open the second product from search result, then add the product to the cart<image>Thought: Click on the second product, identified by the blue spot, to view its details and options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 1092]}<image>Thought: Scroll down to view the second product from the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to proceed with adding the product to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 947]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_0.png",
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_1.png",
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_2.png"
] | 5,174
|
[
{
"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: Open the second product from search result, then add the product to the cart<image>Thought: Scroll down to view the second product from the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to proceed with adding the product to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 947]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully opened the second product from the search results. You then added the Energizer rechargeable batteries to your cart. After reviewing, you decided to proceed with checking out the item in your cart, indicating that your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_1.png",
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_2.png",
"training_data/AITW/aitw_images/single/15660683874142350165.610-763.Open the second product from search result, then add the product to the cart_3.png"
] | 5,175
|
[
{
"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: Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon <image>",
"role": "user"
},
{
"content": "Thought: Click on the blue spot to open the details of the Bose QuietComfort 35 product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [363, 850]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _0.png"
] | 5,176
|
[
{
"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: Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon <image>Thought: Click on the blue spot to open the details of the Bose QuietComfort 35 product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [363, 850]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Bose QuietComfort 35 product shown on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _0.png",
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _1.png"
] | 5,177
|
[
{
"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: Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon <image>Thought: Click on the blue spot to open the details of the Bose QuietComfort 35 product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [363, 850]}<image>Thought: Scroll down to view more details about the Bose QuietComfort 35 product shown on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include the Bose QuietComfort 35 in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 820]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _0.png",
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _1.png",
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _2.png"
] | 5,178
|
[
{
"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: Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon <image>Thought: Scroll down to view more details about the Bose QuietComfort 35 product shown on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to include the Bose QuietComfort 35 in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 820]}<image>",
"role": "user"
},
{
"content": "Thought: You would have opened the searched result for Bose QuietComfort 35 to view its details. You intended to add this product to the cart, which is now shown in your cart summary. Completing your task indicates you successfully added it and are ready for checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _1.png",
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _2.png",
"training_data/AITW/aitw_images/single/4304936349078085278.692-792.Open the searched result related to bose quietcomfort 35 and check the details of this product, then add this item to the shopping cart on amazon _3.png"
] | 5,179
|
[
{
"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: Open Amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon.com to navigate directly to the official Amazon website from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [32, 949]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/883543127338369406.429-524.Open Amazon.com_0.png"
] | 5,180
|
[
{
"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: Open Amazon.com<image>Thought: Click on Amazon.com to navigate directly to the official Amazon website from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [32, 949]}<image>",
"role": "user"
},
{
"content": "Thought: The user accessed Amazon.com successfully, as indicated by the displayed homepage.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/883543127338369406.429-524.Open Amazon.com_0.png",
"training_data/AITW/aitw_images/single/883543127338369406.429-524.Open Amazon.com_1.png"
] | 5,181
|
[
{
"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: Search ebay in the chrome search bar<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar at the top of the Amazon page to input \"ebay\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [355, 107]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_0.png"
] | 5,182
|
[
{
"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: Search ebay in the chrome search bar<image>Thought: Click the search bar at the top of the Amazon page to input \"ebay\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [355, 107]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the Chrome search bar to initiate a search for eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_0.png",
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_1.png"
] | 5,183
|
[
{
"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: Search ebay in the chrome search bar<image>Thought: Click the search bar at the top of the Amazon page to input \"ebay\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [355, 107]}<image>Thought: Type \"ebay\" in the Chrome search bar to initiate a search for eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to quickly navigate to the website from the Google Chrome search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 289]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_0.png",
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_1.png",
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_2.png"
] | 5,184
|
[
{
"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: Search ebay in the chrome search bar<image>Thought: Type \"ebay\" in the Chrome search bar to initiate a search for eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>Thought: Click the eBay link to quickly navigate to the website from the Google Chrome search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 289]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the search for \"ebay\" in the chrome search bar, confirming task completion.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_1.png",
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_2.png",
"training_data/AITW/aitw_images/single/11100298021768616028.177-372.Search ebay in the chrome search bar_3.png"
] | 5,185
|
[
{
"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: go to ebay.com<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the loading of ebay.com as it was typed in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5329938223775541681.364-409.go to ebay.com_0.png"
] | 5,186
|
[
{
"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: go to ebay.com<image>Thought: Press enter to initiate the loading of ebay.com as it was typed in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You successfully accessed ebay.com, confirming that the task to go to the website is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5329938223775541681.364-409.go to ebay.com_0.png",
"training_data/AITW/aitw_images/single/5329938223775541681.364-409.go to ebay.com_1.png"
] | 5,187
|
[
{
"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: Go to google search bar<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate a search or engage with the Google search bar visible on the screen.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8979422586306926416.132-133.Go to google search bar_0.png"
] | 5,188
|
[
{
"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: Go to google search bar<image>Thought: Press enter to initiate a search or engage with the Google search bar visible on the screen.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You have reached the Google search bar at the top of the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8979422586306926416.132-133.Go to google search bar_0.png",
"training_data/AITW/aitw_images/single/8979422586306926416.132-133.Go to google search bar_1.png"
] | 5,189
|
[
{
"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 quine in Wikipedia<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to prepare for entering the search term 'quine'. Type 'quine' in the search bar to execute your query. Press enter to initiate the search for 'quine' on Wikipedia.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 375]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_0.png"
] | 5,190
|
[
{
"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 quine in Wikipedia<image>Thought: Click on the search bar to prepare for entering the search term 'quine'. Type 'quine' in the search bar to execute your query. Press enter to initiate the search for 'quine' on Wikipedia.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 375]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"quine\" in the search box to initiate a Wikipedia search for that topic.\nAction: {\"action\": \"TYPE\", \"value\": \"quine\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_0.png",
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_1.png"
] | 5,191
|
[
{
"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 quine in Wikipedia<image>Thought: Click on the search bar to prepare for entering the search term 'quine'. Type 'quine' in the search bar to execute your query. Press enter to initiate the search for 'quine' on Wikipedia.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 375]}<image>Thought: Type \"quine\" in the search box to initiate a Wikipedia search for that topic.\nAction: {\"action\": \"TYPE\", \"value\": \"quine\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You likely typed \"quine\" into the search bar to find relevant Wikipedia articles. After successfully locating the desired article, you marked your task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_0.png",
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_1.png",
"training_data/AITW/aitw_images/single/2085711417117868651.508-575.Search for quine in Wikipedia_2.png"
] | 5,192
|
[
{
"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: Go to newegg <image>",
"role": "user"
},
{
"content": "Thought: Click the link for Newegg to navigate directly to the website from search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 333]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3211865004610368291.256-287.Go to newegg _0.png"
] | 5,193
|
[
{
"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: Go to newegg <image>Thought: Click the link for Newegg to navigate directly to the website from search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 333]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully navigated to the Newegg website by completing your task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3211865004610368291.256-287.Go to newegg _0.png",
"training_data/AITW/aitw_images/single/3211865004610368291.256-287.Go to newegg _1.png"
] | 5,194
|
[
{
"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: Close pop up then close countries & regions pop up <image>",
"role": "user"
},
{
"content": "Thought: Click the X on the Countries & Regions pop up to close it. Closing this pop up allows for uninterrupted browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [396, 221]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _0.png"
] | 5,195
|
[
{
"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: Close pop up then close countries & regions pop up <image>Thought: Click the X on the Countries & Regions pop up to close it. Closing this pop up allows for uninterrupted browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [396, 221]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to dismiss the countries & regions pop-up and return to main content.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 139]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _0.png",
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _1.png"
] | 5,196
|
[
{
"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: Close pop up then close countries & regions pop up <image>Thought: Click the X on the Countries & Regions pop up to close it. Closing this pop up allows for uninterrupted browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [396, 221]}<image>Thought: Click the X to dismiss the countries & regions pop-up and return to main content.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 139]}<image>",
"role": "user"
},
{
"content": "Thought: Close the countries & regions pop-up to remove it from view, ensuring a smoother browsing experience. Confirming completion indicates all pop-ups were successfully closed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _0.png",
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _1.png",
"training_data/AITW/aitw_images/single/4939120967498719375.838-893.Close pop up then close countries & regions pop up _2.png"
] | 5,197
|
[
{
"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: View item in cart then proceed to checkout<image>",
"role": "user"
},
{
"content": "Thought: Click on \"View Cart\" to see the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [301, 393]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8938883510195139573.546-701.View item in cart then proceed to checkout_0.png"
] | 5,198
|
[
{
"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: View item in cart then proceed to checkout<image>Thought: Click on \"View Cart\" to see the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [301, 393]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Checkout button to proceed with the purchasing process after reviewing items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 984]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8938883510195139573.546-701.View item in cart then proceed to checkout_0.png",
"training_data/AITW/aitw_images/single/8938883510195139573.546-701.View item in cart then proceed to checkout_1.png"
] | 5,199
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.