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: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: You pressed home, likely to exit the settings and return to the main screen for easier navigation to eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR CIRCLE to access the home screen and find the eBay app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 1057]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the eBay entry in the apps list to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 159]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_0.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_1.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_2.png"
] | 9,400
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the NAV BAR CIRCLE to access the home screen and find the eBay app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 1057]}<image>Thought: Click on the eBay entry in the apps list to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 159]}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to access the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 448]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_1.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_2.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_3.png"
] | 9,401
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the eBay entry in the apps list to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 159]}<image>Thought: Click the eBay link to access the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 448]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Clothing & Accessories\" to access the category where I can search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 260]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_2.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_3.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_4.png"
] | 9,402
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the eBay link to access the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 448]}<image>Thought: Click on \"Clothing & Accessories\" to access the category where I can search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 260]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_3.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_4.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_5.png"
] | 9,403
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Clothing & Accessories\" to access the category where I can search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 260]}<image>Thought: Type \"razer blade\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry to view details about the Razer Nari Ultimate.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 311]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_4.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_5.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_6.png"
] | 9,404
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"razer blade\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}<image>Thought: Click the first entry to view details about the Razer Nari Ultimate.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 311]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Razer Nari entry to view details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 594]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_5.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_6.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_7.png"
] | 9,405
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on ebay. Search for razer blade on ebay, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the first entry to view details about the Razer Nari Ultimate.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 311]}<image>Thought: Click the Razer Nari entry to view details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 594]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully navigated to the eBay app, searched for the Razer Blade, selected an item from the search results, added it to your cart, and completed the checkout process.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6949821063048784220_6.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_7.png",
"training_data/AITW/aitw_images/webshopping/6949821063048784220_8.png"
] | 9,406
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to open the browser and access Target's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 1213]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_0.png"
] | 9,407
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click the Chrome icon to open the browser and access Target's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 1213]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on the cart at eBay to check your current items before trying to add the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 102]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_0.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_1.png"
] | 9,408
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click the Chrome icon to open the browser and access Target's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [449, 1213]}<image>Thought: You clicked on the cart at eBay to check your current items before trying to add the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 102]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target\" in the search bar to navigate to the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_0.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_1.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_2.png"
] | 9,409
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: You clicked on the cart at eBay to check your current items before trying to add the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 102]}<image>Thought: Type \"target\" in the search bar to navigate to the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Target option to access the store's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 269]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_1.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_2.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_3.png"
] | 9,410
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Type \"target\" in the search bar to navigate to the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>Thought: Click on the Target option to access the store's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 269]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Target\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 689]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_2.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_3.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_4.png"
] | 9,411
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click on the Target option to access the store's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 269]}<image>Thought: Click the \"Target\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 689]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to begin finding the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 386]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_3.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_4.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_5.png"
] | 9,412
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click the \"Target\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 689]}<image>Thought: Click the Search bar to begin finding the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 386]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g pro\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_4.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_5.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_6.png"
] | 9,413
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click the Search bar to begin finding the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [258, 386]}<image>Thought: Type \"logitech g pro\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"logitech g pro\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [142, 313]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_5.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_6.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_7.png"
] | 9,414
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Type \"logitech g pro\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro\", \"position\": null}<image>Thought: Click on \"logitech g pro\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [142, 313]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Logitech Pro Wireless\" to access the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1002]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_6.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_7.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_8.png"
] | 9,415
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click on \"logitech g pro\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [142, 313]}<image>Thought: Click on \"Logitech Pro Wireless\" to access the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1002]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Logitech Pro Wireless Gaming Mouse for PC.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_7.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_8.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_9.png"
] | 9,416
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click on \"Logitech Pro Wireless\" to access the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1002]}<image>Thought: Scroll down to view more details about the Logitech Pro Wireless Gaming Mouse for PC.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" button to include the Logitech G Pro mouse in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [474, 1210]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_8.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_9.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_10.png"
] | 9,417
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Scroll down to view more details about the Logitech Pro Wireless Gaming Mouse for PC.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" button to include the Logitech G Pro mouse in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [474, 1210]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Decline coverage\" to bypass the protection plan and proceed with the purchase of the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [431, 1190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_9.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_10.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_11.png"
] | 9,418
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g pro to the cart on target<image>Thought: Click \"Add to cart\" button to include the Logitech G Pro mouse in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [474, 1210]}<image>Thought: Click on \"Decline coverage\" to bypass the protection plan and proceed with the purchase of the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [431, 1190]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the item \"Logitech G Pro\" was successfully added to the cart, confirmed by the GUI.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12643847824210588679_10.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_11.png",
"training_data/AITW/aitw_images/webshopping/12643847824210588679_12.png"
] | 9,419
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: You clicked on the CHAT icon to access customer service for assistance with cart operations.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 445]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_0.png"
] | 9,420
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: You clicked on the CHAT icon to access customer service for assistance with cart operations.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 445]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Accept & continue\" to proceed with the Chrome setup and access Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 586]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_0.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_1.png"
] | 9,421
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: You clicked on the CHAT icon to access customer service for assistance with cart operations.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 445]}<image>Thought: Click on \"Accept & continue\" to proceed with the Chrome setup and access Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 586]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"More\" to access additional options related to syncing features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 589]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_0.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_1.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_2.png"
] | 9,422
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Accept & continue\" to proceed with the Chrome setup and access Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 586]}<image>Thought: Click on \"More\" to access additional options related to syncing features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 589]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"No thanks\" to dismiss the sync prompt and proceed with browsing on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 575]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_1.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_2.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_3.png"
] | 9,423
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"More\" to access additional options related to syncing features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 589]}<image>Thought: Click \"No thanks\" to dismiss the sync prompt and proceed with browsing on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 575]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Amazon app icon to open the application for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [334, 596]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_2.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_3.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_4.png"
] | 9,424
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"No thanks\" to dismiss the sync prompt and proceed with browsing on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 575]}<image>Thought: Click on the Amazon app icon to open the application for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [334, 596]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Amazon Basics\" to access the products available in that category before searching for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 266]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_3.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_4.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_5.png"
] | 9,425
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Amazon app icon to open the application for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [334, 596]}<image>Thought: Click on \"Amazon Basics\" to access the products available in that category before searching for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 266]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods\" in the search bar to find the product you want to purchase.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_4.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_5.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_6.png"
] | 9,426
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Amazon Basics\" to access the products available in that category before searching for \"apple airpods.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 266]}<image>Thought: Type \"apple airpods\" in the search bar to find the product you want to purchase.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Select the first entry from the search results for \"apple airpods\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 332]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_5.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_6.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_7.png"
] | 9,427
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"apple airpods\" in the search bar to find the product you want to purchase.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>Thought: Select the first entry from the search results for \"apple airpods\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 332]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"apple airpods\" displayed under the search bar.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_6.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_7.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_8.png"
] | 9,428
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Select the first entry from the search results for \"apple airpods\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 332]}<image>Thought: Scroll down to view more search results for \"apple airpods\" displayed under the search bar.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the first entry of \"Apple Airpods\" to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 406]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_7.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_8.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_9.png"
] | 9,429
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more search results for \"apple airpods\" displayed under the search bar.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the first entry of \"Apple Airpods\" to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 406]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"apple airpods\" on Amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_8.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_9.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_10.png"
] | 9,430
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the first entry of \"Apple Airpods\" to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 406]}<image>Thought: Scroll down to view more search results for \"apple airpods\" on Amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the selected item, including ratings and pricing information.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_9.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_10.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_11.png"
] | 9,431
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more search results for \"apple airpods\" on Amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the selected item, including ratings and pricing information.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more items or options related to \"apple airpods.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_10.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_11.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_12.png"
] | 9,432
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more details about the selected item, including ratings and pricing information.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more items or options related to \"apple airpods.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Clicking X dismisses the delivery alert notification for better visibility to interact with cart functions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 544]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_11.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_12.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_13.png"
] | 9,433
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more items or options related to \"apple airpods.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Clicking X dismisses the delivery alert notification for better visibility to interact with cart functions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 544]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional details about the selected item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_12.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_13.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_14.png"
] | 9,434
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Clicking X dismisses the delivery alert notification for better visibility to interact with cart functions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 544]}<image>Thought: Scroll down to view additional details about the selected item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the product, ensuring all relevant information is accessible before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_13.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_14.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_15.png"
] | 9,435
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view additional details about the selected item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the product, ensuring all relevant information is accessible before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more product details before adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_14.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_15.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_16.png"
] | 9,436
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more details about the product, ensuring all relevant information is accessible before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more product details before adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'Cart' to view the items added. From there, you can access options to clear items. After taking action on the 'Cart', ensure you're ready to add a new item by selecting 'Add to Cart'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 337]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_15.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_16.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_17.png"
] | 9,437
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view more product details before adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the 'Cart' to view the items added. From there, you can access options to clear items. After taking action on the 'Cart', ensure you're ready to add a new item by selecting 'Add to Cart'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 337]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Proceed to checkout\" button to move forward with purchasing the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [242, 531]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_16.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_17.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_18.png"
] | 9,438
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on amazon.com. Search for \"apple airpods\" on amazon.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the 'Cart' to view the items added. From there, you can access options to clear items. After taking action on the 'Cart', ensure you're ready to add a new item by selecting 'Add to Cart'.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 337]}<image>Thought: Click on the \"Proceed to checkout\" button to move forward with purchasing the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [242, 531]}<image>",
"role": "user"
},
{
"content": "Thought: To complete the task of clearing items from the cart, sign in to your Amazon account using your email or phone number. After signing in, search for \"apple airpods\" to find the desired item. Select the first entry to view its details and then add it to your cart. Proceed by selecting checkout to finalize your order, ensuring everything is confirmed as complete afterwards.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5464742232366877977_17.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_18.png",
"training_data/AITW/aitw_images/webshopping/5464742232366877977_19.png"
] | 9,439
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the device's main screen for task execution.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_0.png"
] | 9,440
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to exit the current app and return to the device's main screen for task execution.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 472]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_0.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_1.png"
] | 9,441
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to exit the current app and return to the device's main screen for task execution.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 472]}<image>",
"role": "user"
},
{
"content": "Thought: Click the .Com button to access the Best Buy website for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 84]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_0.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_1.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_2.png"
] | 9,442
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 472]}<image>Thought: Click the .Com button to access the Best Buy website for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 84]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bestbuy\" in the search bar to access the Best Buy website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_1.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_2.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_3.png"
] | 9,443
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the .Com button to access the Best Buy website for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [204, 84]}<image>Thought: Type \"bestbuy\" in the search bar to access the Best Buy website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Best Buy\" to access the website for searching the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 388]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_2.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_3.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_4.png"
] | 9,444
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"bestbuy\" in the search bar to access the Best Buy website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"bestbuy\", \"position\": null}<image>Thought: Click on \"Best Buy\" to access the website for searching the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 388]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to open the search bar for entering \"bose soundsport free.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 263]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_3.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_4.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_5.png"
] | 9,445
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Best Buy\" to access the website for searching the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 388]}<image>Thought: Click the magnifying glass to open the search bar for entering \"bose soundsport free.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 263]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"bose soundsport free\" on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 263]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_4.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_5.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_6.png"
] | 9,446
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"bose soundsport free\" on bestbuy, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the magnifying glass to open the search bar for entering \"bose soundsport free.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 263]}<image>Thought: Click the magnifying glass to initiate a search for \"bose soundsport free\" on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 263]}<image>",
"role": "user"
},
{
"content": "Thought: The search for \"bose soundsport free\" on Best Buy failed, indicating the task could not be completed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12358323418397157959_5.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_6.png",
"training_data/AITW/aitw_images/webshopping/12358323418397157959_7.png"
] | 9,447
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and access the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_0.png"
] | 9,448
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Press home to exit the current app and access the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Target app to access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [319, 1025]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_0.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_1.png"
] | 9,449
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Press home to exit the current app and access the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the Target app to access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [319, 1025]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"target\" to access the Target app and view the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [91, 167]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_0.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_1.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_2.png"
] | 9,450
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Click on the Target app to access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [319, 1025]}<image>Thought: Click on \"target\" to access the Target app and view the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [91, 167]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Target® link to navigate to the official website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 494]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_1.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_2.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_3.png"
] | 9,451
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Click on \"target\" to access the Target app and view the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [91, 167]}<image>Thought: Click on the Target® link to navigate to the official website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 494]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Search bar to begin searching for \"acer predator.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [151, 285]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_2.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_3.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_4.png"
] | 9,452
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Click on the Target® link to navigate to the official website and begin shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 494]}<image>Thought: Click on the Search bar to begin searching for \"acer predator.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [151, 285]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer predator\" into the search bar to find the item to add to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_3.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_4.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_5.png"
] | 9,453
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Click on the Search bar to begin searching for \"acer predator.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [151, 285]}<image>Thought: Type \"acer predator\" into the search bar to find the item to add to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"acer predator triton\" to select the desired item to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 252]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_4.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_5.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_6.png"
] | 9,454
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Type \"acer predator\" into the search bar to find the item to add to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: Click on \"acer predator triton\" to select the desired item to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 252]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the selected \"Acer Predator Triton\" in your shopping cart on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [420, 1076]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_5.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_6.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_7.png"
] | 9,455
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on target. Add \"acer predator\" to the cart on target<image>Thought: Click on \"acer predator triton\" to select the desired item to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 252]}<image>Thought: Click \"Add to cart\" to include the selected \"Acer Predator Triton\" in your shopping cart on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [420, 1076]}<image>",
"role": "user"
},
{
"content": "Thought: The status task complete indicates that the operation to add \"acer predator\" to the cart was successful.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16725884424437946837_6.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_7.png",
"training_data/AITW/aitw_images/webshopping/16725884424437946837_8.png"
] | 9,456
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to open the app launcher and access Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 1350]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_0.png"
] | 9,457
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click the NAV BAR CIRCLE to open the app launcher and access Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 1350]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" in the search bar to find the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_0.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_1.png"
] | 9,458
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click the NAV BAR CIRCLE to open the app launcher and access Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [343, 1350]}<image>Thought: Type \"walmart\" in the search bar to find the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Save Money\" to access Walmart's website and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 293]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_0.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_1.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_2.png"
] | 9,459
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Type \"walmart\" in the search bar to find the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click on \"Save Money\" to access Walmart's website and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 293]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Walmart link to access the shopping site and view your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 1123]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_1.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_2.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_3.png"
] | 9,460
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click on \"Save Money\" to access Walmart's website and view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [354, 293]}<image>Thought: Click the Walmart link to access the shopping site and view your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 1123]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to initiate a search for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 192]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_2.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_3.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_4.png"
] | 9,461
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click the Walmart link to access the shopping site and view your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 1123]}<image>Thought: Click the search bar to initiate a search for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 192]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer thresher\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_3.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_4.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_5.png"
] | 9,462
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click the search bar to initiate a search for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 192]}<image>Thought: Type \"razer thresher\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"razer thresher\" to select the product from the search results and view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 310]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_4.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_5.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_6.png"
] | 9,463
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Type \"razer thresher\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}<image>Thought: Click on \"razer thresher\" to select the product from the search results and view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 310]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"+Add\" button next to \"razer thresher\" to include the item in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 622]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_5.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_6.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_7.png"
] | 9,464
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on walmart. Add \"razer thresher\" to the cart on walmart<image>Thought: Click on \"razer thresher\" to select the product from the search results and view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 310]}<image>Thought: Click the \"+Add\" button next to \"razer thresher\" to include the item in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 622]}<image>",
"role": "user"
},
{
"content": "Thought: The user completed the task, indicating they successfully added \"razer thresher\" to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7285240132527437680_6.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_7.png",
"training_data/AITW/aitw_images/webshopping/7285240132527437680_8.png"
] | 9,465
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the clock app and return to the main screen for web browsing.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_0.png"
] | 9,466
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Press home to exit the clock app and return to the main screen for web browsing.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google Chrome icon to open the browser for accessing Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 956]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_0.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_1.png"
] | 9,467
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Press home to exit the clock app and return to the main screen for web browsing.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the Google Chrome icon to open the browser for accessing Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 956]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Walmart to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 410]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_0.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_1.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_2.png"
] | 9,468
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Click on the Google Chrome icon to open the browser for accessing Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 956]}<image>Thought: Click on Walmart to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 410]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Free two-day shipping\" link to navigate to Walmart's site, where I can search for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 548]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_1.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_2.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_3.png"
] | 9,469
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Click on Walmart to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 410]}<image>Thought: Click the \"Free two-day shipping\" link to navigate to Walmart's site, where I can search for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 548]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search Walmart\" bar to begin looking for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 156]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_2.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_3.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_4.png"
] | 9,470
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Click the \"Free two-day shipping\" link to navigate to Walmart's site, where I can search for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 548]}<image>Thought: Click the \"Search Walmart\" bar to begin looking for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 156]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blackwidow\" into the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blackwidow\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_3.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_4.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_5.png"
] | 9,471
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Click the \"Search Walmart\" bar to begin looking for the Razer BlackWidow.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 156]}<image>Thought: Type \"razer blackwidow\" into the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blackwidow\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"razer blackwidow.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [430, 156]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_4.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_5.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_6.png"
] | 9,472
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Type \"razer blackwidow\" into the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blackwidow\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"razer blackwidow.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [430, 156]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add\" button to place the Razer BlackWidow into the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 812]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_5.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_6.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_7.png"
] | 9,473
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blackwidow to the cart on walmart.com<image>Thought: Click the magnifying glass to initiate a search for \"razer blackwidow.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [430, 156]}<image>Thought: Click the \"Add\" button to place the Razer BlackWidow into the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 812]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully added the Razer BlackWidow to your cart after selecting the \"+\" button.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15464825521204772719_6.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_7.png",
"training_data/AITW/aitw_images/webshopping/15464825521204772719_8.png"
] | 9,474
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access the app drawer for searching Nike.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_0.png"
] | 9,475
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Press home to return to the main screen and access the app drawer for searching Nike.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR RECT to access the navigation options and proceed with the search for Nike.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 1037]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_0.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_1.png"
] | 9,476
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Press home to return to the main screen and access the app drawer for searching Nike.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR RECT to access the navigation options and proceed with the search for Nike.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 1037]}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search query for \"new nike air max 270\" in the Google search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_0.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_1.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_2.png"
] | 9,477
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Click the NAV BAR RECT to access the navigation options and proceed with the search for Nike.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 1037]}<image>Thought: Press enter to execute the search query for \"new nike air max 270\" in the Google search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"nike.com\" in the search bar to navigate directly to the Nike website for further searching.\nAction: {\"action\": \"TYPE\", \"value\": \"nike.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_1.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_2.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_3.png"
] | 9,478
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Press enter to execute the search query for \"new nike air max 270\" in the Google search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Type \"nike.com\" in the search bar to navigate directly to the Nike website for further searching.\nAction: {\"action\": \"TYPE\", \"value\": \"nike.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the link to access Nike's website for further exploration.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 167]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_2.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_3.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_4.png"
] | 9,479
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Type \"nike.com\" in the search bar to navigate directly to the Nike website for further searching.\nAction: {\"action\": \"TYPE\", \"value\": \"nike.com\", \"position\": null}<image>Thought: Click on the link to access Nike's website for further exploration.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 167]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for Nike.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [413, 154]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_3.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_4.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_5.png"
] | 9,480
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Click on the link to access Nike's website for further exploration.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 167]}<image>Thought: Click the magnifying glass to access the search function for Nike.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [413, 154]}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to complete the search for \"new nike air max 270\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_4.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_5.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_6.png"
] | 9,481
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Click the magnifying glass to access the search function for Nike.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [413, 154]}<image>Thought: Press enter to complete the search for \"new nike air max 270\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"nike air max 270\" in the search field to find specific product information.\nAction: {\"action\": \"TYPE\", \"value\": \"nike air max 270\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_5.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_6.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_7.png"
] | 9,482
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the new nike air max 270 on Nike.com<image>Thought: Press enter to complete the search for \"new nike air max 270\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Type \"nike air max 270\" in the search field to find specific product information.\nAction: {\"action\": \"TYPE\", \"value\": \"nike air max 270\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for \"nike air max 270\" on Nike.com, as reflected by the search results displayed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15247077142508480547_6.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_7.png",
"training_data/AITW/aitw_images/webshopping/15247077142508480547_8.png"
] | 9,483
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google app to start searching for Apple AirPods Pro on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 968]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_0.png"
] | 9,484
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on the Google app to start searching for Apple AirPods Pro on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 968]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon\" to initiate a search for the Amazon website in the browser.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_0.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_1.png"
] | 9,485
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on the Google app to start searching for Apple AirPods Pro on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 968]}<image>Thought: Type \"amazon\" to initiate a search for the Amazon website in the browser.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon link to access the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 138]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_0.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_1.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_2.png"
] | 9,486
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Type \"amazon\" to initiate a search for the Amazon website in the browser.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>Thought: Click the Amazon link to access the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 138]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon.com link to access the official website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [98, 345]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_1.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_2.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_3.png"
] | 9,487
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the Amazon link to access the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [136, 138]}<image>Thought: Click the Amazon.com link to access the official website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [98, 345]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Best Sellers to navigate to popular products for easier access to the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 194]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_2.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_3.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_4.png"
] | 9,488
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the Amazon.com link to access the official website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [98, 345]}<image>Thought: Click on Best Sellers to navigate to popular products for easier access to the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 194]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods pro\" into the search bar to locate the desired product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_3.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_4.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_5.png"
] | 9,489
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click on Best Sellers to navigate to popular products for easier access to the search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 194]}<image>Thought: Type \"apple airpods pro\" into the search bar to locate the desired product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"apple airpods pro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 175]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_4.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_5.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_6.png"
] | 9,490
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Type \"apple airpods pro\" into the search bar to locate the desired product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods pro\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"apple airpods pro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 175]}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry to view its details and proceed to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 428]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_5.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_6.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_7.png"
] | 9,491
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to initiate a search for \"apple airpods pro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [496, 175]}<image>Thought: Click the first entry to view its details and proceed to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 428]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Apple AirPods Pro product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_6.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_7.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_8.png"
] | 9,492
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Click the first entry to view its details and proceed to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 428]}<image>Thought: Scroll down to view more details about the Apple AirPods Pro product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional product options and information about the Apple AirPods Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_7.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_8.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_9.png"
] | 9,493
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the Apple AirPods Pro product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view additional product options and information about the Apple AirPods Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the available options for the AirPods Pro 2nd Gen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_8.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_9.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_10.png"
] | 9,494
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view additional product options and information about the Apple AirPods Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the available options for the AirPods Pro 2nd Gen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to place the selected item, Apple AirPods Pro 2nd Gen, in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 990]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_9.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_10.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_11.png"
] | 9,495
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on amazon. Search for \"apple airpods pro\" on amazon, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the available options for the AirPods Pro 2nd Gen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to place the selected item, Apple AirPods Pro 2nd Gen, in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [357, 990]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully added the \"AirPods Pro 2nd Gen\" to your cart, indicating the task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/488777507496023391_10.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_11.png",
"training_data/AITW/aitw_images/webshopping/488777507496023391_12.png"
] | 9,496
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on costco.com. Search for acer predator on costco.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click \"View Cart\" to access the current items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [205, 544]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/413349259180550754_0.png"
] | 9,497
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on costco.com. Search for acer predator on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"View Cart\" to access the current items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [205, 544]}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the item listed in the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 872]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/413349259180550754_0.png",
"training_data/AITW/aitw_images/webshopping/413349259180550754_1.png"
] | 9,498
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on costco.com. Search for acer predator on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"View Cart\" to access the current items in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [205, 544]}<image>Thought: Click Remove to delete the item listed in the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 872]}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the item from the cart and clear all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 793]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/413349259180550754_0.png",
"training_data/AITW/aitw_images/webshopping/413349259180550754_1.png",
"training_data/AITW/aitw_images/webshopping/413349259180550754_2.png"
] | 9,499
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.