messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on costco.com. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the main screen of the device.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_0.png"
] | 6,500
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Press home to exit the current app and return to the main screen of the device.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco app to open it and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 527]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_0.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_1.png"
] | 6,501
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Press home to exit the current app and return to the main screen of the device.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the Costco app to open it and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 527]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"dell alienware\" to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 145]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_0.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_1.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_2.png"
] | 6,502
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Click on the Costco app to open it and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 527]}<image>Thought: Click on \"dell alienware\" to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 145]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Costco Wholesale\" to navigate to the Costco website for your shopping needs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 230]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_1.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_2.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_3.png"
] | 6,503
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Click on \"dell alienware\" to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 145]}<image>Thought: Click on \"Costco Wholesale\" to navigate to the Costco website for your shopping needs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 230]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to start searching for \"dell alienware\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 111]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_2.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_3.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_4.png"
] | 6,504
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Click on \"Costco Wholesale\" to navigate to the Costco website for your shopping needs.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 230]}<image>Thought: Click the Search bar to start searching for \"dell alienware\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 111]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell alienware\" in the search bar to find the specific item on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_3.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_4.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_5.png"
] | 6,505
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Click the Search bar to start searching for \"dell alienware\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 111]}<image>Thought: Type \"dell alienware\" in the search bar to find the specific item on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"dell alienware\" on costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [257, 109]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_4.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_5.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_6.png"
] | 6,506
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Add \"dell alienware\" to the cart on costco.com, then select checkout.<image>Thought: Type \"dell alienware\" in the search bar to find the specific item on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"dell alienware\" on costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [257, 109]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as all items were cleared from the cart and \"dell alienware\" was added successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7249946620942009862_5.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_6.png",
"training_data/AITW/aitw_images/webshopping/7249946620942009862_7.png"
] | 6,507
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the main screen to access Amazon.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_0.png"
] | 6,508
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and return to the main screen to access Amazon.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to open the app drawer and locate the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 1031]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_0.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_1.png"
] | 6,509
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and return to the main screen to access Amazon.com.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR CIRCLE to open the app drawer and locate the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 1031]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" to access the Amazon website where I can search for products.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_0.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_1.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_2.png"
] | 6,510
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the NAV BAR CIRCLE to open the app drawer and locate the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 1031]}<image>Thought: Type \"amazon.com\" to access the Amazon website where I can search for products.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon.com entry to navigate to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 290]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_1.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_2.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_3.png"
] | 6,511
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type \"amazon.com\" to access the Amazon website where I can search for products.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Click the Amazon.com entry to navigate to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 290]}<image>",
"role": "user"
},
{
"content": "Thought: You need to accept the terms to access Chrome and proceed with your Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 1066]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_2.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_3.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_4.png"
] | 6,512
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the Amazon.com entry to navigate to the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 290]}<image>Thought: You need to accept the terms to access Chrome and proceed with your Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 1066]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible; the current screen is for setting up sync, not related to Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 1054]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_3.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_4.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_5.png"
] | 6,513
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: You need to accept the terms to access Chrome and proceed with your Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 1066]}<image>Thought: Status task impossible; the current screen is for setting up sync, not related to Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 1054]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin entering the product name Razer Blade on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_4.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_5.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_6.png"
] | 6,514
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Status task impossible; the current screen is for setting up sync, not related to Amazon shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [424, 1054]}<image>Thought: Click the search bar to begin entering the product name Razer Blade on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 199]}<image>",
"role": "user"
},
{
"content": "Thought: You type \"razer blade\" to initiate a search in the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \" razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_5.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_6.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_7.png"
] | 6,515
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the search bar to begin entering the product name Razer Blade on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 199]}<image>Thought: You type \"razer blade\" to initiate a search in the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \" razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You click \"razer blade\" to select the first entry from the search suggestions in the drop-down menu.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [80, 295]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_6.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_7.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_8.png"
] | 6,516
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: You type \"razer blade\" to initiate a search in the search bar at the top of the screen.\nAction: {\"action\": \"TYPE\", \"value\": \" razer blade\", \"position\": null}<image>Thought: You click \"razer blade\" to select the first entry from the search suggestions in the drop-down menu.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [80, 295]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Razer Blade 14 Gaming Laptop\" entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [271, 481]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_7.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_8.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_9.png"
] | 6,517
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: You click \"razer blade\" to select the first entry from the search suggestions in the drop-down menu.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [80, 295]}<image>Thought: Click on the \"Razer Blade 14 Gaming Laptop\" entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [271, 481]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for 'razer blade' on the Amazon app.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_8.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_9.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_10.png"
] | 6,518
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click on the \"Razer Blade 14 Gaming Laptop\" entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [271, 481]}<image>Thought: Scroll down to view more search results for 'razer blade' on the Amazon app.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more product options and find the one to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_9.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_10.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_11.png"
] | 6,519
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for 'razer blade' on the Amazon app.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more product options and find the one to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include the selected Razer Blade in your shopping cart for purchase later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [280, 820]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_10.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_11.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_12.png"
] | 6,520
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.com. Search for razer blade on amazon.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to see more product options and find the one to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to include the selected Razer Blade in your shopping cart for purchase later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [280, 820]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully added the Razer Blade to your shopping cart on Amazon, completing the task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5502340925538571636_11.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_12.png",
"training_data/AITW/aitw_images/webshopping/5502340925538571636_13.png"
] | 6,521
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen for easier access to Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_0.png"
] | 6,522
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Press home to return to the main screen for easier access to Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLAY button to launch the Walmart app for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 853]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_0.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_1.png"
] | 6,523
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Press home to return to the main screen for easier access to Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the PLAY button to launch the Walmart app for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 853]}<image>",
"role": "user"
},
{
"content": "Thought: Click the three dots to access options for cart management since the item was removed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [471, 60]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_0.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_1.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_2.png"
] | 6,524
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click the PLAY button to launch the Walmart app for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 853]}<image>Thought: Click the three dots to access options for cart management since the item was removed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [471, 60]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view the shopping cart due to missing \"bose soundlink\" item and checkout option.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_1.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_2.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_3.png"
] | 6,525
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click the three dots to access options for cart management since the item was removed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [471, 60]}<image>Thought: Scroll up to view the shopping cart due to missing \"bose soundlink\" item and checkout option.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to search for \"bose soundlink\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [380, 224]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_2.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_3.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_4.png"
] | 6,526
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Scroll up to view the shopping cart due to missing \"bose soundlink\" item and checkout option.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click the magnifying glass to search for \"bose soundlink\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [380, 224]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: The user cannot find \"bose soundlink\" as they are searching for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [291, 154]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_3.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_4.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_5.png"
] | 6,527
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click the magnifying glass to search for \"bose soundlink\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [380, 224]}<image>Thought: Status task impossible: The user cannot find \"bose soundlink\" as they are searching for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [291, 154]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"X\" in the search bar to clear the current search for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 141]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_4.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_5.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_6.png"
] | 6,528
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Status task impossible: The user cannot find \"bose soundlink\" as they are searching for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [291, 154]}<image>Thought: Click the \"X\" in the search bar to clear the current search for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 141]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bose soundlink\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_5.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_6.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_7.png"
] | 6,529
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click the \"X\" in the search bar to clear the current search for \"corsair k70.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 141]}<image>Thought: Type \"bose soundlink\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"bose soundlink\" option in Electronics to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 266]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_6.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_7.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_8.png"
] | 6,530
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Type \"bose soundlink\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose soundlink\", \"position\": null}<image>Thought: Click the \"bose soundlink\" option in Electronics to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 266]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Bose SoundLink Flex Wireless to view product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 639]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_7.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_8.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_9.png"
] | 6,531
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click the \"bose soundlink\" option in Electronics to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 266]}<image>Thought: Click on the Bose SoundLink Flex Wireless to view product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 639]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" button to include the Bose SoundLink in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [441, 981]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_8.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_9.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_10.png"
] | 6,532
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"bose soundlink\" to the cart on walmart, then select checkout.<image>Thought: Click on the Bose SoundLink Flex Wireless to view product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [417, 639]}<image>Thought: Click \"Add to cart\" button to include the Bose SoundLink in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [441, 981]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the item has been successfully added to the cart, confirming the user's action.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17523852144622997538_9.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_10.png",
"training_data/AITW/aitw_images/webshopping/17523852144622997538_11.png"
] | 6,533
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Open the Walmart app to begin clearing the cart. Click on the shopping cart icon to access items. Select all items in the cart for removal. Confirm deletion of items to clear the cart completely. Search for \"logitech g903\" using the search bar at the top of the screen. Add \"logitech g903\" to your cart after finding it in results. Click on proceed to checkout after cart update is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 1178]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_0.png"
] | 6,534
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Open the Walmart app to begin clearing the cart. Click on the shopping cart icon to access items. Select all items in the cart for removal. Confirm deletion of items to clear the cart completely. Search for \"logitech g903\" using the search bar at the top of the screen. Add \"logitech g903\" to your cart after finding it in results. Click on proceed to checkout after cart update is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 1178]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to access the cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 206]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_0.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_1.png"
] | 6,535
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Open the Walmart app to begin clearing the cart. Click on the shopping cart icon to access items. Select all items in the cart for removal. Confirm deletion of items to clear the cart completely. Search for \"logitech g903\" using the search bar at the top of the screen. Add \"logitech g903\" to your cart after finding it in results. Click on proceed to checkout after cart update is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 1178]}<image>Thought: Click on the SHOPPING CART icon to access the cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 206]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to start the process of clearing the cart items. Then type \"logitech g903\" to add the item to your cart. After adding, locate and click the checkout option to proceed with purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [409, 204]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_0.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_1.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_2.png"
] | 6,536
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click on the SHOPPING CART icon to access the cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 206]}<image>Thought: Click on the search bar to start the process of clearing the cart items. Then type \"logitech g903\" to add the item to your cart. After adding, locate and click the checkout option to proceed with purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [409, 204]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g903\" in the search bar to find the product on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_1.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_2.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_3.png"
] | 6,537
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click on the search bar to start the process of clearing the cart items. Then type \"logitech g903\" to add the item to your cart. After adding, locate and click the checkout option to proceed with purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [409, 204]}<image>Thought: Type \"logitech g903\" in the search bar to find the product on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"logitech g903\" and load relevant product results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_2.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_3.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_4.png"
] | 6,538
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Type \"logitech g903\" in the search bar to find the product on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>Thought: Press enter to initiate the search for \"logitech g903\" and load relevant product results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more items for \"logitech g903\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_3.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_4.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_5.png"
] | 6,539
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Press enter to initiate the search for \"logitech g903\" and load relevant product results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more items for \"logitech g903\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"logitech g903\" to view the product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 545]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_4.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_5.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_6.png"
] | 6,540
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Scroll down to see more items for \"logitech g903\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"logitech g903\" to view the product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 545]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen and select items in the cart for clearing.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_5.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_6.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_7.png"
] | 6,541
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"logitech g903\" to view the product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 545]}<image>Thought: Press back to return to the previous screen and select items in the cart for clearing.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g903\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_6.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_7.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_8.png"
] | 6,542
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Press back to return to the previous screen and select items in the cart for clearing.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for \"logitech g903\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the \"Add\" button for the \"logitech g903\" mouse, as it's not visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_7.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_8.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_9.png"
] | 6,543
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Scroll down to view more search results for \"logitech g903\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the \"Add\" button for the \"logitech g903\" mouse, as it's not visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the blue spot to access the \"Add\" button for the Logitech G903. This will add the item to your cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [223, 1122]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_8.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_9.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_10.png"
] | 6,544
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Scroll down to find the \"Add\" button for the \"logitech g903\" mouse, as it's not visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the blue spot to access the \"Add\" button for the Logitech G903. This will add the item to your cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [223, 1122]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the \"logitech g903\" in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [539, 1328]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_9.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_10.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_11.png"
] | 6,545
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click on the blue spot to access the \"Add\" button for the Logitech G903. This will add the item to your cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [223, 1122]}<image>Thought: Click \"Add to cart\" to include the \"logitech g903\" in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [539, 1328]}<image>",
"role": "user"
},
{
"content": "Thought: Decline the protection plan to proceed with the checkout for \"logitech g903\" in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 1328]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_10.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_11.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_12.png"
] | 6,546
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click \"Add to cart\" to include the \"logitech g903\" in your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [539, 1328]}<image>Thought: Decline the protection plan to proceed with the checkout for \"logitech g903\" in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 1328]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View cart\" to access the current items in the shopping cart for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 1329]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_11.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_12.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_13.png"
] | 6,547
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Decline the protection plan to proceed with the checkout for \"logitech g903\" in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [353, 1328]}<image>Thought: Click \"View cart\" to access the current items in the shopping cart for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 1329]}<image>",
"role": "user"
},
{
"content": "Thought: Click Continue to checkout to proceed with the checkout process after reviewing the cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 1268]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_12.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_13.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_14.png"
] | 6,548
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 walmart.com. Add \"logitech g903\" to the cart on walmart.com, then select checkout.<image>Thought: Click \"View cart\" to access the current items in the shopping cart for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 1329]}<image>Thought: Click Continue to checkout to proceed with the checkout process after reviewing the cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 1268]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task, indicating you successfully cleared the cart and added the desired item.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8403786366469675814_13.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_14.png",
"training_data/AITW/aitw_images/webshopping/8403786366469675814_15.png"
] | 6,549
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access pertinent apps for my task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_0.png"
] | 6,550
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Press home to return to the main screen and access pertinent apps for my task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products or options on the Walmart website for adding the Alienware.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_0.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_1.png"
] | 6,551
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Press home to return to the main screen and access pertinent apps for my task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products or options on the Walmart website for adding the Alienware.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the GOOGLE icon to launch the web browser for online shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 341]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_0.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_1.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_2.png"
] | 6,552
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Scroll down to view more products or options on the Walmart website for adding the Alienware.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the GOOGLE icon to launch the web browser for online shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 341]}<image>",
"role": "user"
},
{
"content": "Thought: You want to browse for video games on Walmart, so you click on the Video Games category.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_1.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_2.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_3.png"
] | 6,553
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Click the GOOGLE icon to launch the web browser for online shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [39, 341]}<image>Thought: You want to browse for video games on Walmart, so you click on the Video Games category.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the current search results and refine your query for Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 28]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_2.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_3.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_4.png"
] | 6,554
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: You want to browse for video games on Walmart, so you click on the Video Games category.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 73]}<image>Thought: Click the X to close the current search results and refine your query for Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 28]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_3.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_4.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_5.png"
] | 6,555
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Click the X to close the current search results and refine your query for Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 28]}<image>Thought: Type \"walmart.com\" to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Save Money\" to navigate to the Walmart savings options and find deals for Dell Alienware.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 64]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_4.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_5.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_6.png"
] | 6,556
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Type \"walmart.com\" to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click on \"Save Money\" to navigate to the Walmart savings options and find deals for Dell Alienware.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 64]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search box to begin looking for Dell Alienware products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_5.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_6.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_7.png"
] | 6,557
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Click on \"Save Money\" to navigate to the Walmart savings options and find deals for Dell Alienware.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 64]}<image>Thought: Click the search box to begin looking for Dell Alienware products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 70]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell alienware\" in the search bar to find the item on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_6.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_7.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_8.png"
] | 6,558
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Click the search box to begin looking for Dell Alienware products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 70]}<image>Thought: Type \"dell alienware\" in the search bar to find the item on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click 'dell alienware' to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 106]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_7.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_8.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_9.png"
] | 6,559
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Type \"dell alienware\" in the search bar to find the item on walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}<image>Thought: Click 'dell alienware' to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 106]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button to add the displayed Dell Alienware product to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 363]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_8.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_9.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_10.png"
] | 6,560
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell alienware to the cart on walmart.com<image>Thought: Click 'dell alienware' to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 106]}<image>Thought: Click the PLUS button to add the displayed Dell Alienware product to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 363]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete, indicating that the user successfully added a Dell Alienware item to their cart. The presence of both items suggests they found their desired product and proceeded with the action without issues.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/228267400332311339_9.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_10.png",
"training_data/AITW/aitw_images/webshopping/228267400332311339_11.png"
] | 6,561
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Walmart app icon to open it for searching \"macbook pro 15 inch.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1216]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_0.png"
] | 6,562
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the Walmart app icon to open it for searching \"macbook pro 15 inch.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1216]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible, as the search for \"macbook pro 15 inch\" on Walmart cannot be performed on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [312, 91]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_0.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_1.png"
] | 6,563
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the Walmart app icon to open it for searching \"macbook pro 15 inch.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [485, 1216]}<image>Thought: Status task impossible, as the search for \"macbook pro 15 inch\" on Walmart cannot be performed on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [312, 91]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_0.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_1.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_2.png"
] | 6,564
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Status task impossible, as the search for \"macbook pro 15 inch\" on Walmart cannot be performed on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [312, 91]}<image>Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"walmart.com\" link to access the Walmart website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_1.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_2.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_3.png"
] | 6,565
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click the \"walmart.com\" link to access the Walmart website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 225]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 319]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_2.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_3.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_4.png"
] | 6,566
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the \"walmart.com\" link to access the Walmart website for searching products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 225]}<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 319]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 15 inch\" in the search bar to find desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_3.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_4.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_5.png"
] | 6,567
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 319]}<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"macbook pro 15 inch\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 328]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_4.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_5.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_6.png"
] | 6,568
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>Thought: Click on \"macbook pro 15 inch\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 328]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the search results for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_5.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_6.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_7.png"
] | 6,569
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on \"macbook pro 15 inch\" to select the first entry from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 328]}<image>Thought: Scroll down to view the search results for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the entry for \"RAM 512GB SSD 15'' -..\" to view more details about this MacBook Pro option. Add it to the cart by selecting the blue '+ Add' button, indicating I want to purchase this item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 746]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_6.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_7.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_8.png"
] | 6,570
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the search results for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the entry for \"RAM 512GB SSD 15'' -..\" to view more details about this MacBook Pro option. Add it to the cart by selecting the blue '+ Add' button, indicating I want to purchase this item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 746]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the selected MacBook Pro in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [565, 1355]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_7.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_8.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_9.png"
] | 6,571
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"macbook pro 15 inch\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the entry for \"RAM 512GB SSD 15'' -..\" to view more details about this MacBook Pro option. Add it to the cart by selecting the blue '+ Add' button, indicating I want to purchase this item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 746]}<image>Thought: Click \"Add to cart\" to include the selected MacBook Pro in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [565, 1355]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"macbook pro 15 inch\" on Walmart and selected the first entry. You decided to add it to your cart, which is indicated by the \"Added to cart\" notification on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/303936530823318697_8.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_9.png",
"training_data/AITW/aitw_images/webshopping/303936530823318697_10.png"
] | 6,572
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>",
"role": "user"
},
{
"content": "Thought: Click the TIME icon to access the app for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 1174]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_0.png"
] | 6,573
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the TIME icon to access the app for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 1174]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to potentially reveal the search bar on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [590, 84]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_0.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_1.png"
] | 6,574
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the TIME icon to access the app for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [510, 1174]}<image>Thought: Scroll up to potentially reveal the search bar on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [590, 84]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS icon to open additional options or features related to searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [47, 114]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_0.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_1.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_2.png"
] | 6,575
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Scroll up to potentially reveal the search bar on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [590, 84]}<image>Thought: Click the PLUS icon to open additional options or features related to searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [47, 114]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon.com icon to access the website for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [616, 656]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_1.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_2.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_3.png"
] | 6,576
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the PLUS icon to open additional options or features related to searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [47, 114]}<image>Thought: Click the Amazon.com icon to access the website for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [616, 656]}<image>",
"role": "user"
},
{
"content": "Thought: You click home to return to the main menu to start a new search on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 92]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_2.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_3.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_4.png"
] | 6,577
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the Amazon.com icon to access the website for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [616, 656]}<image>Thought: You click home to return to the main menu to start a new search on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 92]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon.com icon to access the site for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [606, 632]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_3.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_4.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_5.png"
] | 6,578
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: You click home to return to the main menu to start a new search on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 92]}<image>Thought: Click the Amazon.com icon to access the site for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [606, 632]}<image>",
"role": "user"
},
{
"content": "Thought: Type the characters displayed in the image to verify that I am not a robot.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_4.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_5.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_6.png"
] | 6,579
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the Amazon.com icon to access the site for searching mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [606, 632]}<image>Thought: Type the characters displayed in the image to verify that I am not a robot.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}<image>",
"role": "user"
},
{
"content": "Thought: You need to verify your identity by entering the characters shown in the CAPTCHA. You are following instructions given by the interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_5.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_6.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_7.png"
] | 6,580
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Type the characters displayed in the image to verify that I am not a robot.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}<image>Thought: You need to verify your identity by entering the characters shown in the CAPTCHA. You are following instructions given by the interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}<image>",
"role": "user"
},
{
"content": "Thought: Type the characters displayed in the captcha to proceed with the search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"KKLLUM\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_6.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_7.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_8.png"
] | 6,581
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: You need to verify your identity by entering the characters shown in the CAPTCHA. You are following instructions given by the interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 918]}<image>Thought: Type the characters displayed in the captcha to proceed with the search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"KKLLUM\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Continue to proceed past the CAPTCHA and access Amazon for searching keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 1077]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_7.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_8.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_9.png"
] | 6,582
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Type the characters displayed in the captcha to proceed with the search on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"KKLLUM\", \"position\": null}<image>Thought: Click Continue to proceed past the CAPTCHA and access Amazon for searching keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 1077]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search Amazon\" bar to initiate a search for mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [186, 280]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_8.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_9.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_10.png"
] | 6,583
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click Continue to proceed past the CAPTCHA and access Amazon for searching keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 1077]}<image>Thought: Click the \"Search Amazon\" bar to initiate a search for mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [186, 280]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find specific products like mechanical keyboards.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated mechanical keyboard\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_9.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_10.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_11.png"
] | 6,584
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the \"Search Amazon\" bar to initiate a search for mechanical keyboards.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [186, 280]}<image>Thought: Type in the search bar to find specific products like mechanical keyboards.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated mechanical keyboard\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to initiate the search for mechanical keyboards on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_10.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_11.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_12.png"
] | 6,585
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Type in the search bar to find specific products like mechanical keyboards.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated mechanical keyboard\", \"position\": null}<image>Thought: Click the MAGNIFYING GLASS to initiate the search for mechanical keyboards on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_11.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_12.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_13.png"
] | 6,586
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the MAGNIFYING GLASS to initiate the search for mechanical keyboards on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_12.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_13.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_14.png"
] | 6,587
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to submit the search for the best-rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_13.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_14.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_15.png"
] | 6,588
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 best rated mechanical keyboard on Amazon.<image>Thought: Click the magnifying glass to submit the search for best rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>Thought: Click the magnifying glass to submit the search for the best-rated mechanical keyboard on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 283]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates that the user has successfully searched for the best rated mechanical keyboard. The search query “best rated mechanical keyboard” in the search bar shows that they input the exact phrase. The results showing various options confirm a successful search, fulfilling their task of finding high-rated keyboards on Amazon.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5379937772375019174_14.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_15.png",
"training_data/AITW/aitw_images/webshopping/5379937772375019174_16.png"
] | 6,589
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current settings and return to the main screen for searching Amazon.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_0.png"
] | 6,590
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current settings and return to the main screen for searching Amazon.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open the email app, which is likely not necessary for searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_0.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_1.png"
] | 6,591
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current settings and return to the main screen for searching Amazon.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the ENVELOPE to open the email app, which is likely not necessary for searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'Accept & continue' button to proceed with using Chrome and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_0.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_1.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_2.png"
] | 6,592
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Click the ENVELOPE to open the email app, which is likely not necessary for searching on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}<image>Thought: Click the 'Accept & continue' button to proceed with using Chrome and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Accept & continue\" to proceed with using the Chrome browser and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 1272]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_1.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_2.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_3.png"
] | 6,593
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Click the 'Accept & continue' button to proceed with using Chrome and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1161]}<image>Thought: Click on \"Accept & continue\" to proceed with using the Chrome browser and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 1272]}<image>",
"role": "user"
},
{
"content": "Thought: You need to confirm your Google account settings, so click \"Yes, I'm in\" to enable syncing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [628, 1274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_2.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_3.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_4.png"
] | 6,594
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Click on \"Accept & continue\" to proceed with using the Chrome browser and search for Razer Thresher on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 1272]}<image>Thought: You need to confirm your Google account settings, so click \"Yes, I'm in\" to enable syncing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [628, 1274]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon.com to access the website for searching the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [442, 668]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_3.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_4.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_5.png"
] | 6,595
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: You need to confirm your Google account settings, so click \"Yes, I'm in\" to enable syncing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [628, 1274]}<image>Thought: Click on Amazon.com to access the website for searching the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [442, 668]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin typing your query for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 289]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_4.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_5.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_6.png"
] | 6,596
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Click on Amazon.com to access the website for searching the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [442, 668]}<image>Thought: Click the search bar to begin typing your query for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 289]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer thresher\" in the search bar to find the product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_5.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_6.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_7.png"
] | 6,597
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Click the search bar to begin typing your query for \"razer thresher.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 289]}<image>Thought: Type \"razer thresher\" in the search bar to find the product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on 'razer thresher xbox' to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 366]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_6.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_7.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_8.png"
] | 6,598
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 razer thresher on amazon, select the first entry, and add it to the cart.<image>Thought: Type \"razer thresher\" in the search bar to find the product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer thresher\", \"position\": null}<image>Thought: Click on 'razer thresher xbox' to select the desired product from the search suggestions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 366]}<image>",
"role": "user"
},
{
"content": "Thought: Click the star to indicate your preference for the first product in the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 749]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15933023818322763085_7.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_8.png",
"training_data/AITW/aitw_images/webshopping/15933023818322763085_9.png"
] | 6,599
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.