messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for bose quietcomfort 35 on ebay.com<image>Thought: Click \"Search for anything\" to begin the search for Bose QuietComfort 35 on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 316]}<image>Thought: Click the \"Search for anything\" box to begin entering your search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 298]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to enter the query for Bose QuietComfort 35.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_0.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_1.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_2.png"
] | 3,700
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose quietcomfort 35 on ebay.com<image>Thought: Click the \"Search for anything\" box to begin entering your search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 298]}<image>Thought: Type in the search bar to enter the query for Bose QuietComfort 35.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"bose quietcomfort 35\" to select the desired search result for further details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [253, 945]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_1.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_2.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_3.png"
] | 3,701
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose quietcomfort 35 on ebay.com<image>Thought: Type in the search bar to enter the query for Bose QuietComfort 35.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}<image>Thought: Click on \"bose quietcomfort 35\" to select the desired search result for further details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [253, 945]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully entered the search term \"bose quietcomfort 35\" in the eBay search bar, resulting in relevant product listings.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_2.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_3.png",
"training_data/AITW/aitw_images/single/5710478588227661285.254-475.search for bose quietcomfort 35 on ebay.com_4.png"
] | 3,702
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Logitech G502 HERO High Performance Gaming Mouse (910-0054469)<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Logitech G502 HERO\" to open the product details page for more information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [319, 458]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10216814946811914736.1059-1158.Open Logitech G502 HERO High Performance Gaming Mouse (910-0054469)_0.png"
] | 3,703
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Logitech G502 HERO High Performance Gaming Mouse (910-0054469)<image>Thought: Click on \"Logitech G502 HERO\" to open the product details page for more information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [319, 458]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed the Logitech G502 HERO Gaming Mouse product page on Newegg.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10216814946811914736.1059-1158.Open Logitech G502 HERO High Performance Gaming Mouse (910-0054469)_0.png",
"training_data/AITW/aitw_images/single/10216814946811914736.1059-1158.Open Logitech G502 HERO High Performance Gaming Mouse (910-0054469)_1.png"
] | 3,704
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Welcome to Costco Wholesale <image>",
"role": "user"
},
{
"content": "Thought: Click the \"Welcome to Costco Wholesale\" link to access the website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 200]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2265357947222513914.250-301.go to Welcome to Costco Wholesale _0.png"
] | 3,705
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Welcome to Costco Wholesale <image>Thought: Click the \"Welcome to Costco Wholesale\" link to access the website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 200]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed the page titled \"Welcome to Costco Wholesale,\" which fulfills your task requirements.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2265357947222513914.250-301.go to Welcome to Costco Wholesale _0.png",
"training_data/AITW/aitw_images/single/2265357947222513914.250-301.go to Welcome to Costco Wholesale _1.png"
] | 3,706
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 & sign in to checkout<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access your selected items before checking out.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 103]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_0.png"
] | 3,707
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 & sign in to checkout<image>Thought: Click the SHOPPING CART to access your selected items before checking out.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 103]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the 'Sign in to checkout' button at the bottom of the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_0.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_1.png"
] | 3,708
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 & sign in to checkout<image>Thought: Click the SHOPPING CART to access your selected items before checking out.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 103]}<image>Thought: Scroll down to find the 'Sign in to checkout' button at the bottom of the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to see the total and access the checkout button at the bottom of the screen.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_0.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_1.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_2.png"
] | 3,709
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 & sign in to checkout<image>Thought: Scroll down to find the 'Sign in to checkout' button at the bottom of the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to see the total and access the checkout button at the bottom of the screen.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You want to return to the previous screen where sign-in options might be available.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_1.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_2.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_3.png"
] | 3,710
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 & sign in to checkout<image>Thought: Scroll up to see the total and access the checkout button at the bottom of the screen.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: You want to return to the previous screen where sign-in options might be available.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You would navigate to the cart icon to proceed with signing in for checkout. The task is now complete because you successfully accessed your cart and signed in.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_2.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_3.png",
"training_data/AITW/aitw_images/single/949371119911462513.709-957.go to cart & sign in to checkout_4.png"
] | 3,711
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for macbook pro 15 inch in the bestbuy search bar<image>",
"role": "user"
},
{
"content": "Thought: Click on Deals to access discounts which may include the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 212]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_0.png"
] | 3,712
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for macbook pro 15 inch in the bestbuy search bar<image>Thought: Click on Deals to access discounts which may include the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 212]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 15 inch\" in the search bar to find relevant products quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_0.png",
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_1.png"
] | 3,713
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for macbook pro 15 inch in the bestbuy search bar<image>Thought: Click on Deals to access discounts which may include the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [341, 212]}<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find relevant products quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"macbook pro 15\" in the dropdown to select the searched item from search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [160, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_0.png",
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_1.png",
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_2.png"
] | 3,714
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for macbook pro 15 inch in the bestbuy search bar<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find relevant products quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>Thought: Click on \"macbook pro 15\" in the dropdown to select the searched item from search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [160, 225]}<image>",
"role": "user"
},
{
"content": "Thought: You would have typed \"macbook pro 15 inch\" in the Best Buy search bar to find relevant products. The status task complete indicates successful execution of the search without errors.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_1.png",
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_2.png",
"training_data/AITW/aitw_images/single/11254242581222238241.882-1206.search for macbook pro 15 inch in the bestbuy search bar_3.png"
] | 3,715
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: proceed to checkout<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Proceed to checkout\" button to start the payment process for the selected item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [307, 245]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13041761259861315293.927-1042.proceed to checkout_0.png"
] | 3,716
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: proceed to checkout<image>Thought: Click the \"Proceed to checkout\" button to start the payment process for the selected item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [307, 245]}<image>",
"role": "user"
},
{
"content": "Thought: You signed in to your Amazon account, allowing the checkout process to proceed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13041761259861315293.927-1042.proceed to checkout_0.png",
"training_data/AITW/aitw_images/single/13041761259861315293.927-1042.proceed to checkout_1.png"
] | 3,717
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 google go to search bar and type amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Click GOOGLE to launch the Google search app for accessing the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 1033]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_0.png"
] | 3,718
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 google go to search bar and type amazon.com<image>Thought: Click GOOGLE to launch the Google search app for accessing the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 1033]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" in the search bar to navigate to the website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_0.png",
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_1.png"
] | 3,719
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 google go to search bar and type amazon.com<image>Thought: Click GOOGLE to launch the Google search app for accessing the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 1033]}<image>Thought: Type \"amazon.com\" in the search bar to navigate to the website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You typed \"amazon.com\" in the search bar to initiate a web search for that site. After completing the input, you confirmed the action, showing your task is finished.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_0.png",
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_1.png",
"training_data/AITW/aitw_images/single/8745262031355837182.4-187.open google go to search bar and type amazon.com_2.png"
] | 3,720
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g pro <image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to execute the search for Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 289]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7348707871868575956.712-745.search for logitech g pro _0.png"
] | 3,721
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g pro <image>Thought: Click the magnifying glass to execute the search for Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 289]}<image>",
"role": "user"
},
{
"content": "Thought: The search for \"logitech g pro\" returned no exact matches, indicating a need to explore related products.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7348707871868575956.712-745.search for logitech g pro _0.png",
"training_data/AITW/aitw_images/single/7348707871868575956.712-745.search for logitech g pro _1.png"
] | 3,722
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 result of logitech g933 in bestbuy.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the first result to access the product page for Logitech G935.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [217, 903]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10576349040690085220.840-909.open the first result of logitech g933 in bestbuy.com_0.png"
] | 3,723
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 result of logitech g933 in bestbuy.com<image>Thought: Click on the first result to access the product page for Logitech G935.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [217, 903]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on the first search result, confirming you found the Logitech G933. The task is now complete as you successfully accessed the product page on BestBuy.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10576349040690085220.840-909.open the first result of logitech g933 in bestbuy.com_0.png",
"training_data/AITW/aitw_images/single/10576349040690085220.840-909.open the first result of logitech g933 in bestbuy.com_1.png"
] | 3,724
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 home and open Chrome<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access the app drawer for Chrome.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_0.png"
] | 3,725
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 home and open Chrome<image>Thought: Press home to return to the main screen and access the app drawer for Chrome.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the home screen to return to the main interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 922]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_0.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_1.png"
] | 3,726
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 home and open Chrome<image>Thought: Press home to return to the main screen and access the app drawer for Chrome.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the home screen to return to the main interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 922]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon at the bottom to open the browser.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 922]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_0.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_1.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_2.png"
] | 3,727
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 home and open Chrome<image>Thought: Click on the home screen to return to the main interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 922]}<image>Thought: Click the Chrome icon at the bottom to open the browser.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 922]}<image>",
"role": "user"
},
{
"content": "Thought: Open the home screen to access the Chrome browser. Once on the home screen, locate and tap on the Chrome app icon. Confirm that I successfully opened Chrome for my browsing needs.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_1.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_2.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-1028.Go home and open Chrome_3.png"
] | 3,728
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco<image>",
"role": "user"
},
{
"content": "Thought: Type \"costco\" in the search bar to initiate a query for Costco's website or information.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_0.png"
] | 3,729
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco<image>Thought: Type \"costco\" in the search bar to initiate a query for Costco's website or information.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to submit the search term \"costco\" in the search bar for results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_0.png",
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_1.png"
] | 3,730
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco<image>Thought: Type \"costco\" in the search bar to initiate a query for Costco's website or information.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>Thought: Press enter to submit the search term \"costco\" in the search bar for results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You searched for Costco by entering the website URL and found the relevant page, so task completes successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_0.png",
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_1.png",
"training_data/AITW/aitw_images/single/5492278795149393035.144-168.Search costco_2.png"
] | 3,731
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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<image>",
"role": "user"
},
{
"content": "Thought: Click \"Go to Cart\" to view selected items before proceeding with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 1318]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12898135047656434364.771-864.Go to cart_0.png"
] | 3,732
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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<image>Thought: Click \"Go to Cart\" to view selected items before proceeding with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [174, 1318]}<image>",
"role": "user"
},
{
"content": "Thought: The user has accessed the cart page, indicating they want to view their selected items and total cost. The presence of a visible cart summary confirms they successfully navigated to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12898135047656434364.771-864.Go to cart_0.png",
"training_data/AITW/aitw_images/single/12898135047656434364.771-864.Go to cart_1.png"
] | 3,733
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING in Newegg.com and then go to Search bar<image>",
"role": "user"
},
{
"content": "Thought: Click CONTINUE SHOPPING to navigate away from the empty cart message and start exploring products. After continuing shopping, look for the Search bar to find specific items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [175, 406]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_0.png"
] | 3,734
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING in Newegg.com and then go to Search bar<image>Thought: Click CONTINUE SHOPPING to navigate away from the empty cart message and start exploring products. After continuing shopping, look for the Search bar to find specific items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [175, 406]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search bar for further shopping options on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 125]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_0.png",
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_1.png"
] | 3,735
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING in Newegg.com and then go to Search bar<image>Thought: Click CONTINUE SHOPPING to navigate away from the empty cart message and start exploring products. After continuing shopping, look for the Search bar to find specific items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [175, 406]}<image>Thought: Click the magnifying glass to access the search bar for further shopping options on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 125]}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to access the search bar for further shopping options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [334, 130]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_0.png",
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_1.png",
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_2.png"
] | 3,736
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING in Newegg.com and then go to Search bar<image>Thought: Click the magnifying glass to access the search bar for further shopping options on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 125]}<image>Thought: Click the MAGNIFYING GLASS to access the search bar for further shopping options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [334, 130]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on CONTINUE SHOPPING to return to the shopping experience on Newegg.com. You then recognized the Search bar at the top of the screen as the next logical step for finding items. Since you successfully navigated through these steps, you can confirm that your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_1.png",
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_2.png",
"training_data/AITW/aitw_images/single/15529516037020227210.755-998.go to CONTINUE SHOPPING in Newegg.com and then go to Search bar_3.png"
] | 3,737
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Click Google to access the web browser for searching amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 1289]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_0.png"
] | 3,738
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Click Google to access the web browser for searching amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 1289]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon\" in the search bar to find the website for online shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_0.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_1.png"
] | 3,739
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Click Google to access the web browser for searching amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 1289]}<image>Thought: Type \"amazon\" in the search bar to find the website for online shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to submit the search for amazon.com and access the website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_0.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_1.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_2.png"
] | 3,740
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Type \"amazon\" in the search bar to find the website for online shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>Thought: Press enter to submit the search for amazon.com and access the website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the link \"Welkom bij Amazon - Groot aanbod, kleine prijzen\" to access Amazon's homepage for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 448]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_1.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_2.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_3.png"
] | 3,741
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Press enter to submit the search for amazon.com and access the website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the link \"Welkom bij Amazon - Groot aanbod, kleine prijzen\" to access Amazon's homepage for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 448]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar labeled \"Zoeken Amazon\" to initiate a search for products on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 246]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_2.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_3.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_4.png"
] | 3,742
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Click the link \"Welkom bij Amazon - Groot aanbod, kleine prijzen\" to access Amazon's homepage for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 448]}<image>Thought: Click the search bar labeled \"Zoeken Amazon\" to initiate a search for products on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 246]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g910\" into the search bar to initiate the product search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_3.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_4.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_5.png"
] | 3,743
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Click the search bar labeled \"Zoeken Amazon\" to initiate a search for products on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 246]}<image>Thought: Type \"logitech g910\" into the search bar to initiate the product search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to initiate the search function for 'logitech g910'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 256]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_4.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_5.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_6.png"
] | 3,744
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Type \"logitech g910\" into the search bar to initiate the product search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910\", \"position\": null}<image>Thought: Click the MAGNIFYING GLASS to initiate the search function for 'logitech g910'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 256]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Cookies aanvaarden\" button to agree to the cookie policy and enable full site functionality.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [520, 1212]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_5.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_6.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_7.png"
] | 3,745
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com then search for logitech g910 on amazon.com<image>Thought: Click the MAGNIFYING GLASS to initiate the search function for 'logitech g910'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 256]}<image>Thought: Click the \"Cookies aanvaarden\" button to agree to the cookie policy and enable full site functionality.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [520, 1212]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for \"logitech g910\" on amazon.com by entering the query and obtaining results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_6.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_7.png",
"training_data/AITW/aitw_images/single/10082878812118506532.16-383.search for amazon.com then search for logitech g910 on amazon.com_8.png"
] | 3,746
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on target and empty the cart on target<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon in the upper right corner to view the contents of your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 227]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_0.png"
] | 3,747
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on target and empty the cart on target<image>Thought: Click the SHOPPING CART icon in the upper right corner to view the contents of your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 227]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X icon to remove the item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 678]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_0.png",
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_1.png"
] | 3,748
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on target and empty the cart on target<image>Thought: Click the SHOPPING CART icon in the upper right corner to view the contents of your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 227]}<image>Thought: Click the X icon to remove the item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 678]}<image>",
"role": "user"
},
{
"content": "Thought: The GUI indicates there are no items in the cart, confirming the task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_0.png",
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_1.png",
"training_data/AITW/aitw_images/single/8530627649688364594.202-366.Show the shopping cart on target and empty the cart on target_2.png"
] | 3,749
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 first product from results <image>",
"role": "user"
},
{
"content": "Thought: Click the STAR to select the first product from the search results for Beats Solo 3.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 702]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2974524692942155180.700-747.Go to first product from results _0.png"
] | 3,750
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 first product from results <image>Thought: Click the STAR to select the first product from the search results for Beats Solo 3.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 702]}<image>",
"role": "user"
},
{
"content": "Thought: You would have clicked on the first product to select it from the search results, completing your task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2974524692942155180.700-747.Go to first product from results _0.png",
"training_data/AITW/aitw_images/single/2974524692942155180.700-747.Go to first product from results _1.png"
] | 3,751
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 chrome and go to search bar.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access Chrome, as you need to go there for the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1140]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._0.png"
] | 3,752
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 chrome and go to search bar.<image>Thought: Click the ENVELOPE icon to access Chrome, as you need to go there for the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1140]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to enter a search query. Type \"beats solo 3\" to find specific headphones. Press enter to initiate the search on Amazon. Status task complete, as you have successfully searched for \"beats solo 3\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 85]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._0.png",
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._1.png"
] | 3,753
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 chrome and go to search bar.<image>Thought: Click the ENVELOPE icon to access Chrome, as you need to go there for the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1140]}<image>Thought: Click the search bar to enter a search query. Type \"beats solo 3\" to find specific headphones. Press enter to initiate the search on Amazon. Status task complete, as you have successfully searched for \"beats solo 3\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 85]}<image>",
"role": "user"
},
{
"content": "Thought: You have accessed the Chrome interface and found the search bar ready for input, indicating your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._0.png",
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._1.png",
"training_data/AITW/aitw_images/single/8888960531606202600.104-228.Go to chrome and go to search bar._2.png"
] | 3,754
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar in google chrome then search for walmart.com<image>",
"role": "user"
},
{
"content": "Thought: You would click the URL \"secure.m.newegg.com/shopping\" to access that webpage. Since you need to reach the search bar, locate it at the top. Once focused on the search bar, type \"walmart.com\" to perform your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 112]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_0.png"
] | 3,755
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar in google chrome then search for walmart.com<image>Thought: You would click the URL \"secure.m.newegg.com/shopping\" to access that webpage. Since you need to reach the search bar, locate it at the top. Once focused on the search bar, type \"walmart.com\" to perform your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 112]}<image>",
"role": "user"
},
{
"content": "Thought: Focus on the search bar to enter the desired website, which is walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_0.png",
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_1.png"
] | 3,756
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar in google chrome then search for walmart.com<image>Thought: You would click the URL \"secure.m.newegg.com/shopping\" to access that webpage. Since you need to reach the search bar, locate it at the top. Once focused on the search bar, type \"walmart.com\" to perform your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 112]}<image>Thought: Focus on the search bar to enter the desired website, which is walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue link for walmart.com to access the website directly from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_0.png",
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_1.png",
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_2.png"
] | 3,757
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar in google chrome then search for walmart.com<image>Thought: Focus on the search bar to enter the desired website, which is walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click the blue link for walmart.com to access the website directly from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 225]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely opened Google Chrome to access the internet. The blue arrow indicates they have successfully navigated to the search bar. Clicking on the search bar allows them to type in their query. They efficiently entered \"walmart.com\" to access that website. Since they reached Walmart's website, they confirm their task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_1.png",
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_2.png",
"training_data/AITW/aitw_images/single/16555884756782061822.389-579.Go to search bar in google chrome then search for walmart.com_3.png"
] | 3,758
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add\" to place the Aluminum 2-in-1 Magnetic Wireless Charging Stand into the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 723]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_0.png"
] | 3,759
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart<image>Thought: Click \"Add\" to place the Aluminum 2-in-1 Magnetic Wireless Charging Stand into the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 723]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to find the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" item in the product list.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_0.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_1.png"
] | 3,760
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart<image>Thought: Click \"Add\" to place the Aluminum 2-in-1 Magnetic Wireless Charging Stand into the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 723]}<image>Thought: Scroll up to find the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" item in the product list.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to see the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" in the search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_0.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_1.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_2.png"
] | 3,761
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart<image>Thought: Scroll up to find the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" item in the product list.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to see the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" in the search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to view the items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [491, 152]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_1.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_2.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_3.png"
] | 3,762
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart<image>Thought: Scroll up to see the \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" in the search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on the SHOPPING CART icon to view the items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [491, 152]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the task of adding \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" to the cart. The cart now displays two items, confirming the addition.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_2.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_3.png",
"training_data/AITW/aitw_images/single/11507283552556381364.787-932.Add \"Aluminum 2-in-1 Magnetic Wireless Charging Stand\" into the cart, then go to the Cart_4.png"
] | 3,763
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco search bar: acer predator<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer predator\" in the search bar to find specific products available at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_0.png"
] | 3,764
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco search bar: acer predator<image>Thought: Type \"acer predator\" in the search bar to find specific products available at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You press enter to submit the search query in the Costco search bar for \"acer predator.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_0.png",
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_1.png"
] | 3,765
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 costco search bar: acer predator<image>Thought: Type \"acer predator\" in the search bar to find specific products available at Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: You press enter to submit the search query in the Costco search bar for \"acer predator.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: The user completed the task of entering \"acer predator\" in the Costco search bar, resulting in successful search results displayed on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_0.png",
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_1.png",
"training_data/AITW/aitw_images/single/13806719090864996503.191-226.enter in costco search bar: acer predator_2.png"
] | 3,766
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bar search bar of google chrome then go to target : expect more. pay less<image>",
"role": "user"
},
{
"content": "Thought: Click on the Best Buy URL to access the website. Accessing this site may have been a detour from your intended task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [307, 104]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_0.png"
] | 3,767
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bar search bar of google chrome then go to target : expect more. pay less<image>Thought: Click on the Best Buy URL to access the website. Accessing this site may have been a detour from your intended task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [307, 104]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Target : Expect More. Pay Less.\" entry to navigate to the Target website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 530]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_0.png",
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_1.png"
] | 3,768
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bar search bar of google chrome then go to target : expect more. pay less<image>Thought: Click on the Best Buy URL to access the website. Accessing this site may have been a detour from your intended task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [307, 104]}<image>Thought: Click on the \"Target : Expect More. Pay Less.\" entry to navigate to the Target website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 530]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully navigated to the Target website, which confirms your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_0.png",
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_1.png",
"training_data/AITW/aitw_images/single/1191288202584120347.121-160.go to the bar search bar of google chrome then go to target : expect more. pay less_2.png"
] | 3,769
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Costco Wholesale<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Costco Wholesale\" link to access the Costco website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 421]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2022935876992484098.543-600.Open Costco Wholesale_0.png"
] | 3,770
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Costco Wholesale<image>Thought: Click the \"Costco Wholesale\" link to access the Costco website directly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 421]}<image>",
"role": "user"
},
{
"content": "Thought: Opening Costco Wholesale indicates successful navigation to the website, confirming the user accessed the desired content.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2022935876992484098.543-600.Open Costco Wholesale_0.png",
"training_data/AITW/aitw_images/single/2022935876992484098.543-600.Open Costco Wholesale_1.png"
] | 3,771
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar on bestbuy <image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate a search on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [317, 265]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2242486643930131989.257-389.Go to search bar on bestbuy _0.png"
] | 3,772
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 search bar on bestbuy <image>Thought: Click the Search bar to initiate a search on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [317, 265]}<image>",
"role": "user"
},
{
"content": "Thought: You likely accessed the search bar to find specific products on Best Buy.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2242486643930131989.257-389.Go to search bar on bestbuy _0.png",
"training_data/AITW/aitw_images/single/2242486643930131989.257-389.Go to search bar on bestbuy _1.png"
] | 3,773
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Set up not then proceed to checkout <image>",
"role": "user"
},
{
"content": "Thought: Click \"Set Up Now\" to initiate the subscription process for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 868]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _0.png"
] | 3,774
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Set up not then proceed to checkout <image>Thought: Click \"Set Up Now\" to initiate the subscription process for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 868]}<image>",
"role": "user"
},
{
"content": "Thought: Click the yellow \"Proceed to checkout\" button to transition from shopping to completing the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [330, 577]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _0.png",
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _1.png"
] | 3,775
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Set up not then proceed to checkout <image>Thought: Click \"Set Up Now\" to initiate the subscription process for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 868]}<image>Thought: Click the yellow \"Proceed to checkout\" button to transition from shopping to completing the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [330, 577]}<image>",
"role": "user"
},
{
"content": "Thought: Complete the sign-in process so I can proceed to checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _0.png",
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _1.png",
"training_data/AITW/aitw_images/single/5741780163851832348.743-1164.Set up not then proceed to checkout _2.png"
] | 3,776
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>",
"role": "user"
},
{
"content": "Thought: Click the Walmart tab to access its contents for searching items. Scroll down to find the search bar where you can enter your query. Type \"panasonic triple a rechargeable batteries\" into the search bar to look for the specific products you need. Press enter to execute the search and see results related to your query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 784]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _0.png"
] | 3,777
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>Thought: Click the Walmart tab to access its contents for searching items. Scroll down to find the search bar where you can enter your query. Type \"panasonic triple a rechargeable batteries\" into the search bar to look for the specific products you need. Press enter to execute the search and see results related to your query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 784]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Walmart tab to access the shopping interface. Scroll down to find the search bar at the top of the page. Type \"panasonic triple a rechargeable batteries\" in the search bar to initiate a product search. Press enter to submit your query and view search results for batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _0.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _1.png"
] | 3,778
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>Thought: Click the Walmart tab to access its contents for searching items. Scroll down to find the search bar where you can enter your query. Type \"panasonic triple a rechargeable batteries\" into the search bar to look for the specific products you need. Press enter to execute the search and see results related to your query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 784]}<image>Thought: Click the Walmart tab to access the shopping interface. Scroll down to find the search bar at the top of the page. Type \"panasonic triple a rechargeable batteries\" in the search bar to initiate a product search. Press enter to submit your query and view search results for batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 190]}<image>",
"role": "user"
},
{
"content": "Thought: Click X to clear the previous search for \"razer blade 15\" in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _0.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _1.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _2.png"
] | 3,779
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>Thought: Click the Walmart tab to access the shopping interface. Scroll down to find the search bar at the top of the page. Type \"panasonic triple a rechargeable batteries\" in the search bar to initiate a product search. Press enter to submit your query and view search results for batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 190]}<image>Thought: Click X to clear the previous search for \"razer blade 15\" in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 190]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"panasonic triple a\" into the search bar to find specific batteries.\nAction: {\"action\": \"TYPE\", \"value\": \"panasonic triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _1.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _2.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _3.png"
] | 3,780
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>Thought: Click X to clear the previous search for \"razer blade 15\" in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 190]}<image>Thought: Type \"panasonic triple a\" into the search bar to find specific batteries.\nAction: {\"action\": \"TYPE\", \"value\": \"panasonic triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"rechargeable batteries\" to select the correct item from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 372]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _2.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _3.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _4.png"
] | 3,781
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart tab then go to search bar and search for panasonic triple a rechargeable batteries <image>Thought: Type \"panasonic triple a\" into the search bar to find specific batteries.\nAction: {\"action\": \"TYPE\", \"value\": \"panasonic triple a\", \"position\": null}<image>Thought: Click on \"rechargeable batteries\" to select the correct item from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 372]}<image>",
"role": "user"
},
{
"content": "Thought: The user completed the task by successfully searching for \"panasonic triple a rechargeable batteries\" in the Walmart search bar, which indicates they found the desired products.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _3.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _4.png",
"training_data/AITW/aitw_images/single/6889105385802826653.285-472.Go to walmart tab then go to search bar and search for panasonic triple a rechargeable batteries _5.png"
] | 3,782
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING <image>",
"role": "user"
},
{
"content": "Thought: Click on the CONTINUE SHOPPING button to initiate further shopping actions after the cart is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [190, 588]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11584043761487107714.366-415.go to CONTINUE SHOPPING _0.png"
] | 3,783
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 CONTINUE SHOPPING <image>Thought: Click on the CONTINUE SHOPPING button to initiate further shopping actions after the cart is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [190, 588]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely navigated the interface to find an option to continue shopping, achieving their goal.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/11584043761487107714.366-415.go to CONTINUE SHOPPING _0.png",
"training_data/AITW/aitw_images/single/11584043761487107714.366-415.go to CONTINUE SHOPPING _1.png"
] | 3,784
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose soundlink mini on bestbuy.com<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate the process of finding Bose SoundLink Mini on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 180]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_0.png"
] | 3,785
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose soundlink mini on bestbuy.com<image>Thought: Click the Search bar to initiate the process of finding Bose SoundLink Mini on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 180]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bose soundlink mini\" in the search bar to initiate a product search on Best Buy's website.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink mini\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_0.png",
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_1.png"
] | 3,786
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose soundlink mini on bestbuy.com<image>Thought: Click the Search bar to initiate the process of finding Bose SoundLink Mini on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 180]}<image>Thought: Type \"bose soundlink mini\" in the search bar to initiate a product search on Best Buy's website.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink mini\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"bose soundlink mini\" to select the suggested search term for my query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 188]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_0.png",
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_1.png",
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_2.png"
] | 3,787
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 bose soundlink mini on bestbuy.com<image>Thought: Type \"bose soundlink mini\" in the search bar to initiate a product search on Best Buy's website.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink mini\", \"position\": null}<image>Thought: Click on \"bose soundlink mini\" to select the suggested search term for my query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 188]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"bose soundlink mini\" in the search bar. You wanted to find available products for that specific model on Best Buy. The results displayed show exactly what you were looking for, confirming the task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_1.png",
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_2.png",
"training_data/AITW/aitw_images/single/4448307078676507095.653-825.search for bose soundlink mini on bestbuy.com_3.png"
] | 3,788
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: google search bar, type macbook pro on newegg and choose first suggestion d<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to gain access for typing your query. Type \"macbook pro\" in the search bar to specify the product you are looking for.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 86]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_0.png"
] | 3,789
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: google search bar, type macbook pro on newegg and choose first suggestion d<image>Thought: Click the search bar to gain access for typing your query. Type \"macbook pro\" in the search bar to specify the product you are looking for.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 86]}<image>",
"role": "user"
},
{
"content": "Thought: You are attempting to perform a Google search, so continue typing \"macbook pro\" in the search bar. Since you have already typed “macbook pro on newegg,” it's necessary to look for relevant suggestions that appear below the search bar. After completing your input, you should see suggestions; choosing the first one will help you quickly access related content without additional typing.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro on newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_0.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_1.png"
] | 3,790
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: google search bar, type macbook pro on newegg and choose first suggestion d<image>Thought: Click the search bar to gain access for typing your query. Type \"macbook pro\" in the search bar to specify the product you are looking for.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [444, 86]}<image>Thought: You are attempting to perform a Google search, so continue typing \"macbook pro\" in the search bar. Since you have already typed “macbook pro on newegg,” it's necessary to look for relevant suggestions that appear below the search bar. After completing your input, you should see suggestions; choosing the first one will help you quickly access related content without additional typing.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro on newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to enter the query for MacBook Pro on Newegg. Type \"MacBook Pro\" using the keyboard for specific results. Press enter to initiate the search and view suggestions. Select the first suggestion related to Newegg from the list presented.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 86]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_0.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_1.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_2.png"
] | 3,791
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: google search bar, type macbook pro on newegg and choose first suggestion d<image>Thought: You are attempting to perform a Google search, so continue typing \"macbook pro\" in the search bar. Since you have already typed “macbook pro on newegg,” it's necessary to look for relevant suggestions that appear below the search bar. After completing your input, you should see suggestions; choosing the first one will help you quickly access related content without additional typing.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro on newegg\", \"position\": null}<image>Thought: Click the search bar to enter the query for MacBook Pro on Newegg. Type \"MacBook Pro\" using the keyboard for specific results. Press enter to initiate the search and view suggestions. Select the first suggestion related to Newegg from the list presented.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 86]}<image>",
"role": "user"
},
{
"content": "Thought: Continue typing \"macbook pro on newegg\" in the Google search bar to complete the query.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro on n\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_1.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_2.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_3.png"
] | 3,792
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: google search bar, type macbook pro on newegg and choose first suggestion d<image>Thought: Click the search bar to enter the query for MacBook Pro on Newegg. Type \"MacBook Pro\" using the keyboard for specific results. Press enter to initiate the search and view suggestions. Select the first suggestion related to Newegg from the list presented.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 86]}<image>Thought: Continue typing \"macbook pro on newegg\" in the Google search bar to complete the query.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro on n\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You typed \"macbook pro on newegg\" in the search bar to initiate a search. You chose the first suggestion to directly access relevant results. The task is complete as you successfully searched for the items you wanted.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_2.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_3.png",
"training_data/AITW/aitw_images/single/5552698871263375565.342-403.google search bar, type macbook pro on newegg and choose first suggestion d_4.png"
] | 3,793
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for logitech g910 on target<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g910\" into the search bar to initiate a product search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910 \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_0.png"
] | 3,794
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for logitech g910 on target<image>Thought: Type \"logitech g910\" into the search bar to initiate a product search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910 \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search for \"logitech g910.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 186]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_0.png",
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_1.png"
] | 3,795
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for logitech g910 on target<image>Thought: Type \"logitech g910\" into the search bar to initiate a product search on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g910 \", \"position\": null}<image>Thought: Click the magnifying glass to initiate the search for \"logitech g910.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 186]}<image>",
"role": "user"
},
{
"content": "Thought: The search for \"logitech g910\" was successful, displaying 66 results in the GUI.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_0.png",
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_1.png",
"training_data/AITW/aitw_images/single/840834809329424232.395-649.Search for logitech g910 on target_2.png"
] | 3,796
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 google chrome and go to search bar.<image>",
"role": "user"
},
{
"content": "Thought: Open Google Chrome to access the search bar for entering queries. The task is complete as the search bar displays \"newegg near me.\"\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/18256980855991977739.89-89.Open google chrome and go to search bar._0.png"
] | 3,797
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay.com then go to cart on ebay.com<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: You clicked a link for NewEgg instead of searching for eBay, so the desired action can't be completed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 82]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3849204048007529287.180-517.search for ebay.com then go to cart on ebay.com_0.png"
] | 3,798
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay.com then go to cart on ebay.com<image>Thought: Status task impossible: You clicked a link for NewEgg instead of searching for eBay, so the desired action can't be completed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 82]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the search bar to find eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3849204048007529287.180-517.search for ebay.com then go to cart on ebay.com_0.png",
"training_data/AITW/aitw_images/single/3849204048007529287.180-517.search for ebay.com then go to cart on ebay.com_1.png"
] | 3,799
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.