messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on ebay.com. Add macbook pro 15 inch to the cart on ebay.com, then select checkout.<image>Thought: You click the item labeled \"LOADED!\" to view its details and proceed with the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 564]}<image>Thought: Scroll down to view more details about the MacBook Pro being added to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more details about the MacBook Pro before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13028595113451240648_10.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_11.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_12.png"
] | 5,300
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on ebay.com. Add macbook pro 15 inch to the cart on ebay.com, then select checkout.<image>Thought: Scroll down to view more details about the MacBook Pro being added to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more details about the MacBook Pro before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"View in cart\" to review the items added to the cart before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 635]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13028595113451240648_11.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_12.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_13.png"
] | 5,301
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on ebay.com. Add macbook pro 15 inch to the cart on ebay.com, then select checkout.<image>Thought: Scroll down to see more details about the MacBook Pro before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"View in cart\" to review the items added to the cart before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 635]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Go to checkout\" to proceed with the purchase of the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [271, 456]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13028595113451240648_12.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_13.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_14.png"
] | 5,302
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on ebay.com. Add macbook pro 15 inch to the cart on ebay.com, then select checkout.<image>Thought: Click on \"View in cart\" to review the items added to the cart before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [231, 635]}<image>Thought: Click \"Go to checkout\" to proceed with the purchase of the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [271, 456]}<image>",
"role": "user"
},
{
"content": "Thought: You likely completed the task by finalizing your purchase on eBay after adding the MacBook Pro to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13028595113451240648_13.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_14.png",
"training_data/AITW/aitw_images/webshopping/13028595113451240648_15.png"
] | 5,303
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Amazon app icon on the home screen for further action.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_0.png"
] | 5,304
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Scroll down to find the Amazon app icon on the home screen for further action.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You click Google to open the search engine for looking up information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 352]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_0.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_1.png"
] | 5,305
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Scroll down to find the Amazon app icon on the home screen for further action.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You click Google to open the search engine for looking up information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 352]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible as the operation does not align with looking up headphones on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [93, 41]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_0.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_1.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_2.png"
] | 5,306
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: You click Google to open the search engine for looking up information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 352]}<image>Thought: Status task impossible as the operation does not align with looking up headphones on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [93, 41]}<image>",
"role": "user"
},
{
"content": "Thought: Click the MIC to initiate voice search for headphones, aiming for convenience in finding information quickly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 74]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_1.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_2.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_3.png"
] | 5,307
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Status task impossible as the operation does not align with looking up headphones on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [93, 41]}<image>Thought: Click the MIC to initiate voice search for headphones, aiming for convenience in finding information quickly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 74]}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'X' to dismiss the current search result, as it does not pertain to headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 34]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_2.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_3.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_4.png"
] | 5,308
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Click the MIC to initiate voice search for headphones, aiming for convenience in finding information quickly.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 74]}<image>Thought: Click the 'X' to dismiss the current search result, as it does not pertain to headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 34]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"the best rated wireless headphones on amazon\" to begin looking for the best rated headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [135, 43]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_3.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_4.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_5.png"
] | 5,309
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Click the 'X' to dismiss the current search result, as it does not pertain to headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 34]}<image>Thought: Click on \"the best rated wireless headphones on amazon\" to begin looking for the best rated headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [135, 43]}<image>",
"role": "user"
},
{
"content": "Thought: You want to search for the headphones, so type in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on Amazon.\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_4.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_5.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_6.png"
] | 5,310
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: Click on \"the best rated wireless headphones on amazon\" to begin looking for the best rated headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [135, 43]}<image>Thought: You want to search for the headphones, so type in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on Amazon.\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on amazon.com to navigate to the Amazon website for searching headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [101, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_5.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_6.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_7.png"
] | 5,311
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Look up the best rated headphones on Amazon.<image>Thought: You want to search for the headphones, so type in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"the best rated headphones on Amazon.\", \"position\": null}<image>Thought: Click on amazon.com to navigate to the Amazon website for searching headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [101, 70]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully used Google to search for the best rated headphones on Amazon. The information displayed confirms your query and the result indicates task completion.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14961098628463119649_6.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_7.png",
"training_data/AITW/aitw_images/webshopping/14961098628463119649_8.png"
] | 5,312
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>",
"role": "user"
},
{
"content": "Thought: Click on the NAV BAR CIRCLE to access the app drawer for searching Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [265, 1042]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_0.png"
] | 5,313
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click on the NAV BAR CIRCLE to access the app drawer for searching Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [265, 1042]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Best Buy\" in the search bar to locate the retailer for the new Nintendo Switch.\nAction: {\"action\": \"TYPE\", \"value\": \"Best Buy\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_0.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_1.png"
] | 5,314
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click on the NAV BAR CIRCLE to access the app drawer for searching Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [265, 1042]}<image>Thought: Type \"Best Buy\" in the search bar to locate the retailer for the new Nintendo Switch.\nAction: {\"action\": \"TYPE\", \"value\": \"Best Buy\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"new Nintendo Switch\" in the search bar to find relevant information on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_0.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_1.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_2.png"
] | 5,315
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Type \"Best Buy\" in the search bar to locate the retailer for the new Nintendo Switch.\nAction: {\"action\": \"TYPE\", \"value\": \"Best Buy\", \"position\": null}<image>Thought: Type \"new Nintendo Switch\" in the search bar to find relevant information on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"best buy mountain view\" to view the store's details and check for the new Nintendo Switch availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 123]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_1.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_2.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_3.png"
] | 5,316
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Type \"new Nintendo Switch\" in the search bar to find relevant information on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Click on \"best buy mountain view\" to view the store's details and check for the new Nintendo Switch availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 123]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results and information related to the Nintendo Switch at Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_2.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_3.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_4.png"
] | 5,317
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click on \"best buy mountain view\" to view the store's details and check for the new Nintendo Switch availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 123]}<image>Thought: Scroll down to view more search results and information related to the Nintendo Switch at Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Best Buy link to access the website for further searching options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 491]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_3.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_4.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_5.png"
] | 5,318
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Scroll down to view more search results and information related to the Nintendo Switch at Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Best Buy link to access the website for further searching options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 491]}<image>",
"role": "user"
},
{
"content": "Thought: Select the United States to access the correct Best Buy website for your location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 398]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_4.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_5.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_6.png"
] | 5,319
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click the Best Buy link to access the website for further searching options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 491]}<image>Thought: Select the United States to access the correct Best Buy website for your location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 398]}<image>",
"role": "user"
},
{
"content": "Thought: Select the United States to proceed with shopping on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 377]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_5.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_6.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_7.png"
] | 5,320
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Select the United States to access the correct Best Buy website for your location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 398]}<image>Thought: Select the United States to proceed with shopping on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 377]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search button to initiate a search for the new Nintendo Switch on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 195]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_6.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_7.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_8.png"
] | 5,321
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Select the United States to proceed with shopping on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 377]}<image>Thought: Click the Search button to initiate a search for the new Nintendo Switch on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 195]}<image>",
"role": "user"
},
{
"content": "Thought: Allow the website to access location for better search results on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [458, 624]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_7.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_8.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_9.png"
] | 5,322
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click the Search button to initiate a search for the new Nintendo Switch on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 195]}<image>Thought: Allow the website to access location for better search results on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [458, 624]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate a search for the new Nintendo Switch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 129]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_8.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_9.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_10.png"
] | 5,323
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Allow the website to access location for better search results on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [458, 624]}<image>Thought: Click the Search bar to initiate a search for the new Nintendo Switch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 129]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Nintendo switch\" in the search bar to look for the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"Nintendo switch\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_9.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_10.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_11.png"
] | 5,324
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click the Search bar to initiate a search for the new Nintendo Switch.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [82, 129]}<image>Thought: Type \"Nintendo switch\" in the search bar to look for the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"Nintendo switch\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Switch Consoles\" to access the category of Nintendo Switch products listed in the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_10.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_11.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_12.png"
] | 5,325
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Type \"Nintendo switch\" in the search bar to look for the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"Nintendo switch\", \"position\": null}<image>Thought: Click \"Switch Consoles\" to access the category of Nintendo Switch products listed in the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 190]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Switch Consoles\" to view available Nintendo Switch products specifically targeted for that category.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [165, 187]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_11.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_12.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_13.png"
] | 5,326
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new Nintendo switch on Best Buy<image>Thought: Click \"Switch Consoles\" to access the category of Nintendo Switch products listed in the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 190]}<image>Thought: Click on \"Switch Consoles\" to view available Nintendo Switch products specifically targeted for that category.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [165, 187]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully completed the search for the Nintendo Switch on Best Buy, as indicated by the status task complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8886770195566448467_12.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_13.png",
"training_data/AITW/aitw_images/webshopping/8886770195566448467_14.png"
] | 5,327
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>",
"role": "user"
},
{
"content": "Thought: Press home to navigate away from the settings and return to the main screen to access Newegg.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_0.png"
] | 5,328
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Press home to navigate away from the settings and return to the main screen to access Newegg.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app needed for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 907]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_0.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_1.png"
] | 5,329
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Press home to navigate away from the settings and return to the main screen to access Newegg.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click PLAY to open the app needed for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 907]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access the email or messaging app for potential order confirmation or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 906]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_0.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_1.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_2.png"
] | 5,330
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click PLAY to open the app needed for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 907]}<image>Thought: Click the ENVELOPE icon to access the email or messaging app for potential order confirmation or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 906]}<image>",
"role": "user"
},
{
"content": "Thought: Click the shopping cart link to view items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [303, 65]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_1.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_2.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_3.png"
] | 5,331
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click the ENVELOPE icon to access the email or messaging app for potential order confirmation or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 906]}<image>Thought: Click the shopping cart link to view items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [303, 65]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg\" in the search bar to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_2.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_3.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_4.png"
] | 5,332
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click the shopping cart link to view items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [303, 65]}<image>Thought: Type \"newegg\" in the search bar to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to search for the Razer Nari on Newegg's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_3.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_4.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_5.png"
] | 5,333
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Type \"newegg\" in the search bar to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>Thought: Press enter to search for the Razer Nari on Newegg's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Model # to search for the Razer Nari headset. Click on Item # to select the specific product to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [177, 192]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_4.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_5.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_6.png"
] | 5,334
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Press enter to search for the Razer Nari on Newegg's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on Model # to search for the Razer Nari headset. Click on Item # to select the specific product to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [177, 192]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer nari\" in the search bar to find the product quickly on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \" razer nari\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_5.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_6.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_7.png"
] | 5,335
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click on Model # to search for the Razer Nari headset. Click on Item # to select the specific product to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [177, 192]}<image>Thought: Type \"razer nari\" in the search bar to find the product quickly on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \" razer nari\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer nari\" in the search bar to find the product quickly. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_6.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_7.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_8.png"
] | 5,336
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Type \"razer nari\" in the search bar to find the product quickly on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \" razer nari\", \"position\": null}<image>Thought: Type \"razer nari\" in the search bar to find the product quickly. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Razer Nari to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 842]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_7.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_8.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_9.png"
] | 5,337
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Type \"razer nari\" in the search bar to find the product quickly. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on the Razer Nari to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 842]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"ADD TO CART\" button to start purchasing the Razer Nari headset.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 1049]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_8.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_9.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_10.png"
] | 5,338
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click on the Razer Nari to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 842]}<image>Thought: Click the \"ADD TO CART\" button to start purchasing the Razer Nari headset.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 1049]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ADD button to include the Razer Nari in the shopping cart, completing the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [36, 1024]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_9.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_10.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_11.png"
] | 5,339
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on newegg<image>Thought: Click the \"ADD TO CART\" button to start purchasing the Razer Nari headset.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 1049]}<image>Thought: Click the ADD button to include the Razer Nari in the shopping cart, completing the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [36, 1024]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task successfully; the Razer Nari was added to your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10555154384063316795_10.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_11.png",
"training_data/AITW/aitw_images/webshopping/10555154384063316795_12.png"
] | 5,340
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome app to open it and search for \"logitech g933\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1222]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_0.png"
] | 5,341
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click the Chrome app to open it and search for \"logitech g933\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1222]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: The user is on eBay, not Target, making their shopping goal unattainable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [328, 93]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_0.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_1.png"
] | 5,342
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click the Chrome app to open it and search for \"logitech g933\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1222]}<image>Thought: Status task impossible: The user is on eBay, not Target, making their shopping goal unattainable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [328, 93]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"target\" to navigate to the Target website where I can search for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [145, 1146]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_0.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_1.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_2.png"
] | 5,343
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Status task impossible: The user is on eBay, not Target, making their shopping goal unattainable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [328, 93]}<image>Thought: Click on \"target\" to navigate to the Target website where I can search for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [145, 1146]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Season\" to access seasonal products available at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 733]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_1.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_2.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_3.png"
] | 5,344
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click on \"target\" to navigate to the Target website where I can search for the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [145, 1146]}<image>Thought: Click on \"Season\" to access seasonal products available at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 733]}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to locate the product \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 369]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_2.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_3.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_4.png"
] | 5,345
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click on \"Season\" to access seasonal products available at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 733]}<image>Thought: Click Search to locate the product \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 369]}<image>",
"role": "user"
},
{
"content": "Thought: You type \"logitech g933\" in the search field to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_3.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_4.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_5.png"
] | 5,346
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click Search to locate the product \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 369]}<image>Thought: You type \"logitech g933\" in the search field to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to search for \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [559, 204]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_4.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_5.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_6.png"
] | 5,347
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: You type \"logitech g933\" in the search field to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}<image>Thought: Click the magnifying glass to search for \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [559, 204]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to include the Logitech G933 headset in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [524, 1403]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_5.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_6.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_7.png"
] | 5,348
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g933\" to the cart on target, then select checkout.<image>Thought: Click the magnifying glass to search for \"logitech g933\" in the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [559, 204]}<image>Thought: Click the \"Add to cart\" button to include the Logitech G933 headset in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [524, 1403]}<image>",
"role": "user"
},
{
"content": "Thought: You likely added the \"logitech g933\" to the cart by clicking on the \"Add to cart\" button. After adding it, you completed your task which confirms your shopping action was successful.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13467176555321833943_6.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_7.png",
"training_data/AITW/aitw_images/webshopping/13467176555321833943_8.png"
] | 5,349
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to open your email or messaging app for account access or confirmation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 912]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_0.png"
] | 5,350
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the ENVELOPE icon to open your email or messaging app for account access or confirmation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 912]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize you are on the Newegg sign-in page, not Best Buy. Click the \"Continue with Guest Checkout\" button to proceed without signing in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_0.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_1.png"
] | 5,351
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the ENVELOPE icon to open your email or messaging app for account access or confirmation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 912]}<image>Thought: Recognize you are on the Newegg sign-in page, not Best Buy. Click the \"Continue with Guest Checkout\" button to proceed without signing in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Click on bestbuy.com to load the website and access the shopping cart feature.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 456]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_0.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_1.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_2.png"
] | 5,352
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Recognize you are on the Newegg sign-in page, not Best Buy. Click the \"Continue with Guest Checkout\" button to proceed without signing in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [269, 67]}<image>Thought: Click on bestbuy.com to load the website and access the shopping cart feature.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 456]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 213]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_1.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_2.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_3.png"
] | 5,353
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on bestbuy.com to load the website and access the shopping cart feature.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 456]}<image>Thought: Click the SHOPPING CART icon to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 213]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to browse items in the cart and prepare to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_2.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_3.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_4.png"
] | 5,354
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART icon to access the cart for clearing items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 213]}<image>Thought: Scroll down to browse items in the cart and prepare to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more items or options related to the shopping cart on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_3.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_4.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_5.png"
] | 5,355
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to browse items in the cart and prepare to clear it.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more items or options related to the shopping cart on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options or details about the shopping cart items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_4.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_5.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_6.png"
] | 5,356
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more items or options related to the shopping cart on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options or details about the shopping cart items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the arrow to navigate and see more items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 1024]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_5.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_6.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_7.png"
] | 5,357
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more options or details about the shopping cart items.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the arrow to navigate and see more items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 1024]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Remove option to eliminate items in the shopping cart and start fresh.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 1028]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_6.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_7.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_8.png"
] | 5,358
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on the arrow to navigate and see more items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 1024]}<image>Thought: Click the Remove option to eliminate items in the shopping cart and start fresh.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 1028]}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the item from the shopping cart. This action clears the cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [356, 1028]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_7.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_8.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_9.png"
] | 5,359
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the Remove option to eliminate items in the shopping cart and start fresh.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [359, 1028]}<image>Thought: Click Remove to delete the item from the shopping cart. This action clears the cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [356, 1028]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the shopping cart and check the items added.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_8.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_9.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_10.png"
] | 5,360
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click Remove to delete the item from the shopping cart. This action clears the cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [356, 1028]}<image>Thought: Scroll down to view the shopping cart and check the items added.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Remove\" to delete unwanted items from the shopping cart as part of the clearing process on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 650]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_9.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_10.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_11.png"
] | 5,361
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the shopping cart and check the items added.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Remove\" to delete unwanted items from the shopping cart as part of the clearing process on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 650]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view the removed item notification for confirmation before clearing the cart.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_10.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_11.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_12.png"
] | 5,362
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click \"Remove\" to delete unwanted items from the shopping cart as part of the clearing process on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 650]}<image>Thought: Scroll up to view the removed item notification for confirmation before clearing the cart.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view the cart items and confirm removal of unwanted items from bestbuy.com.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_11.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_12.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_13.png"
] | 5,363
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll up to view the removed item notification for confirmation before clearing the cart.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view the cart items and confirm removal of unwanted items from bestbuy.com.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the selected item from the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [339, 627]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_12.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_13.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_14.png"
] | 5,364
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll up to view the cart items and confirm removal of unwanted items from bestbuy.com.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click Remove to delete the selected item from the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [339, 627]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the blue Search button to initiate a search for \"duracell triple a.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [327, 152]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_13.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_14.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_15.png"
] | 5,365
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click Remove to delete the selected item from the shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [339, 627]}<image>Thought: Click on the blue Search button to initiate a search for \"duracell triple a.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [327, 152]}<image>",
"role": "user"
},
{
"content": "Thought: You want to search for \"duracell triple a\" using the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \"duracell triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_14.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_15.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_16.png"
] | 5,366
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on the blue Search button to initiate a search for \"duracell triple a.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [327, 152]}<image>Thought: You want to search for \"duracell triple a\" using the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \"duracell triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search for duracell triple a on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 157]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_15.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_16.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_17.png"
] | 5,367
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on bestbuy.com. Search for duracell triple a on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: You want to search for \"duracell triple a\" using the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \"duracell triple a\", \"position\": null}<image>Thought: Click the magnifying glass to initiate the search for duracell triple a on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 157]}<image>",
"role": "user"
},
{
"content": "Thought: Status task complete indicates I searched for \"duracell triple a\" on bestbuy.com, but found no results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9270917422096241684_16.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_17.png",
"training_data/AITW/aitw_images/webshopping/9270917422096241684_18.png"
] | 5,368
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Search for \"jbl charge 4\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: status task impossible\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1191584364244286710_0.png"
] | 5,369
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 1222]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_0.png"
] | 5,370
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 1222]}<image>",
"role": "user"
},
{
"content": "Thought: Since the user is on a sign-in page of Best Buy instead of Costco, clicking the three dots may indicate an option to refresh or change the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [612, 87]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_0.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_1.png"
] | 5,371
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 1222]}<image>Thought: Since the user is on a sign-in page of Best Buy instead of Costco, clicking the three dots may indicate an option to refresh or change the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [612, 87]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the $24.99 entry to select the item I want to purchase from Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [541, 412]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_0.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_1.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_2.png"
] | 5,372
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Since the user is on a sign-in page of Best Buy instead of Costco, clicking the three dots may indicate an option to refresh or change the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [612, 87]}<image>Thought: Click on the $24.99 entry to select the item I want to purchase from Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [541, 412]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view more search results for \"asus rog\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_1.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_2.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_3.png"
] | 5,373
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the $24.99 entry to select the item I want to purchase from Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [541, 412]}<image>Thought: Scroll up to view more search results for \"asus rog\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to check if any results for \"asus rog\" were missed above the current view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_2.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_3.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_4.png"
] | 5,374
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll up to view more search results for \"asus rog\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to check if any results for \"asus rog\" were missed above the current view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible since the search for \"asus rog\" did not yield any matching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [419, 257]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_3.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_4.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_5.png"
] | 5,375
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll up to check if any results for \"asus rog\" were missed above the current view.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Status task impossible since the search for \"asus rog\" did not yield any matching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [419, 257]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked the 'X' to close the suggestion dropdown, allowing you to focus on entering \"asus rog\" directly into the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [589, 269]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_4.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_5.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_6.png"
] | 5,376
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible since the search for \"asus rog\" did not yield any matching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [419, 257]}<image>Thought: You clicked the 'X' to close the suggestion dropdown, allowing you to focus on entering \"asus rog\" directly into the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [589, 269]}<image>",
"role": "user"
},
{
"content": "Thought: You typed \"macbook\" in the search bar instead of \"asus rog,\" indicating a mistake in your search term. The GUI shows no matching results for \"macbook,\" prompting consideration of a different search term. Correctly inputting \"asus rog\" is necessary to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_5.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_6.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_7.png"
] | 5,377
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: You clicked the 'X' to close the suggestion dropdown, allowing you to focus on entering \"asus rog\" directly into the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [589, 269]}<image>Thought: You typed \"macbook\" in the search bar instead of \"asus rog,\" indicating a mistake in your search term. The GUI shows no matching results for \"macbook,\" prompting consideration of a different search term. Correctly inputting \"asus rog\" is necessary to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the search dropdown and start a new search for \"asus rog.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [595, 255]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_6.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_7.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_8.png"
] | 5,378
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: You typed \"macbook\" in the search bar instead of \"asus rog,\" indicating a mistake in your search term. The GUI shows no matching results for \"macbook,\" prompting consideration of a different search term. Correctly inputting \"asus rog\" is necessary to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>Thought: Click the X to close the search dropdown and start a new search for \"asus rog.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [595, 255]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"asus rog\" in the search bar to find relevant products on Costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_7.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_8.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_9.png"
] | 5,379
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the X to close the search dropdown and start a new search for \"asus rog.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [595, 255]}<image>Thought: Type \"asus rog\" in the search bar to find relevant products on Costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Desktop - Intel\" to view more details about the ASUS ROG product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 603]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_8.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_9.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_10.png"
] | 5,380
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"asus rog\" in the search bar to find relevant products on Costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"asus rog\", \"position\": null}<image>Thought: Click on \"Desktop - Intel\" to view more details about the ASUS ROG product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 603]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the \"ASUS ROG Gaming Desktop\" listed on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_9.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_10.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_11.png"
] | 5,381
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Desktop - Intel\" to view more details about the ASUS ROG product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 603]}<image>Thought: Scroll down to view more details about the \"ASUS ROG Gaming Desktop\" listed on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options for the ASUS ROG product and its details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_10.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_11.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_12.png"
] | 5,382
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more details about the \"ASUS ROG Gaming Desktop\" listed on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options for the ASUS ROG product and its details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the entry to view more details about the ASUS ROG product listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [538, 1143]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_11.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_12.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_13.png"
] | 5,383
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more options for the ASUS ROG product and its details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the entry to view more details about the ASUS ROG product listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [538, 1143]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the ASUS ROG product before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_12.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_13.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_14.png"
] | 5,384
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the entry to view more details about the ASUS ROG product listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [538, 1143]}<image>Thought: Scroll down to view more details about the ASUS ROG product before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the selected item for purchase in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_13.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_14.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_15.png"
] | 5,385
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more details about the ASUS ROG product before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to include the selected item for purchase in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View Cart\" to review the items added and proceed with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_14.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_15.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_16.png"
] | 5,386
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"Add to Cart\" to include the selected item for purchase in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}<image>Thought: Click \"View Cart\" to review the items added and proceed with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}<image>",
"role": "user"
},
{
"content": "Thought: You click on the Checkout button to proceed with purchasing the selected item in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 1389]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_15.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_16.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_17.png"
] | 5,387
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"asus rog\" on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"View Cart\" to review the items added and proceed with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [399, 565]}<image>Thought: You click on the Checkout button to proceed with purchasing the selected item in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 1389]}<image>",
"role": "user"
},
{
"content": "Thought: The task is to search for \"asus rog\", so the user likely accessed the Costco website, intending to find a specific product. The status task complete indicates that all operations necessary to complete the purchase were successfully performed, including signing in, searching, selecting an item, adding it to the cart, and proceeding to checkout. The blue spot in the screenshot suggests user interaction with necessary GUI elements such as filling in email and password for sign-in before accessing product listings.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10047955806307243018_16.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_17.png",
"training_data/AITW/aitw_images/webshopping/10047955806307243018_18.png"
] | 5,388
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>",
"role": "user"
},
{
"content": "Thought: Click the MIC icon to activate voice search for quickly finding a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 916]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_0.png"
] | 5,389
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Click the MIC icon to activate voice search for quickly finding a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 916]}<image>",
"role": "user"
},
{
"content": "Thought: Click the browser icon to open it for searching a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 915]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_0.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_1.png"
] | 5,390
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Click the MIC icon to activate voice search for quickly finding a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 916]}<image>Thought: Click the browser icon to open it for searching a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 915]}<image>",
"role": "user"
},
{
"content": "Thought: Click the link to find articles or deals that may include bike options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 77]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_0.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_1.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_2.png"
] | 5,391
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Click the browser icon to open it for searching a new bike on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 915]}<image>Thought: Click the link to find articles or deals that may include bike options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 77]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"new bike on walmart\" in the search bar to initiate a search for bikes available at Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"new bike on walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_1.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_2.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_3.png"
] | 5,392
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Click the link to find articles or deals that may include bike options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 77]}<image>Thought: Type \"new bike on walmart\" in the search bar to initiate a search for bikes available at Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"new bike on walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to submit the search query \"new bike on walmart\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_2.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_3.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_4.png"
] | 5,393
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Type \"new bike on walmart\" in the search bar to initiate a search for bikes available at Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"new bike on walmart\", \"position\": null}<image>Thought: Press enter to submit the search query \"new bike on walmart\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more bike options available on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_3.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_4.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_5.png"
] | 5,394
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Press enter to submit the search query \"new bike on walmart\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more bike options available on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Bikes - Walmart.com\" link to navigate directly to the bike selection on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 968]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_4.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_5.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_6.png"
] | 5,395
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a new bike on Walmart.<image>Thought: Scroll down to view more bike options available on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Bikes - Walmart.com\" link to navigate directly to the bike selection on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 968]}<image>",
"role": "user"
},
{
"content": "Thought: You would have searched for bikes on Walmart and completed the task successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11491058108437765286_5.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_6.png",
"training_data/AITW/aitw_images/webshopping/11491058108437765286_7.png"
] | 5,396
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on ebay.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access eBay notifications or messages that may relate to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1138]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4278112097286508506_0.png"
] | 5,397
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on ebay.<image>Thought: Click the ENVELOPE icon to access eBay notifications or messages that may relate to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1138]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on a link to Amazon's sign-in page instead of eBay, indicating possible confusion or error.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [322, 71]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4278112097286508506_0.png",
"training_data/AITW/aitw_images/webshopping/4278112097286508506_1.png"
] | 5,398
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on ebay.<image>Thought: Click the ENVELOPE icon to access eBay notifications or messages that may relate to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1138]}<image>Thought: You clicked on a link to Amazon's sign-in page instead of eBay, indicating possible confusion or error.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [322, 71]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Fashion\" link to access eBay's Fashion section where the shopping cart may be located.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 298]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4278112097286508506_0.png",
"training_data/AITW/aitw_images/webshopping/4278112097286508506_1.png",
"training_data/AITW/aitw_images/webshopping/4278112097286508506_2.png"
] | 5,399
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.