messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result of usb-c to usb-b and go down to cart section, then Add to cart<image>Thought: Click on \"Braided\" to access the product details for the first result.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 604]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the cart section for adding the item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_0.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_1.png"
] | 4,400
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result of usb-c to usb-b and go down to cart section, then Add to cart<image>Thought: Click on \"Braided\" to access the product details for the first result.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 604]}<image>Thought: Scroll down to view the cart section for adding the item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the cart section located below the product details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_0.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_1.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_2.png"
] | 4,401
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result of usb-c to usb-b and go down to cart section, then Add to cart<image>Thought: Scroll down to view the cart section for adding the item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the cart section located below the product details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to proceed with purchasing the selected USB-C to USB-B cable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [382, 1163]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_1.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_2.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_3.png"
] | 4,402
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result of usb-c to usb-b and go down to cart section, then Add to cart<image>Thought: Scroll down to view the cart section located below the product details.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to proceed with purchasing the selected USB-C to USB-B cable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [382, 1163]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully opened the first result for USB-C to USB-B and navigated to the cart section. You added the item to your cart, confirming that your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_2.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_3.png",
"training_data/AITW/aitw_images/single/12812562161825678788.1117-1229.Open first result of usb-c to usb-b and go down to cart section, then Add to cart_4.png"
] | 4,403
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove items from the cart, fulfilling the task of deleting all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_0.png"
] | 4,404
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>Thought: Click DELETE to remove items from the cart, fulfilling the task of deleting all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove the item from the cart as part of clearing it completely.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_0.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_1.png"
] | 4,405
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>Thought: Click DELETE to remove items from the cart, fulfilling the task of deleting all items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}<image>Thought: Click DELETE to remove the item from the cart as part of clearing it completely.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}<image>",
"role": "user"
},
{
"content": "Thought: Click DELETE to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_0.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_1.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_2.png"
] | 4,406
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>Thought: Click DELETE to remove the item from the cart as part of clearing it completely.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 356]}<image>Thought: Click DELETE to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}<image>",
"role": "user"
},
{
"content": "Thought: Click the DELETE button to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_1.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_2.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_3.png"
] | 4,407
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>Thought: Click DELETE to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}<image>Thought: Click the DELETE button to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the cart icon to access the items in the shopping cart. This allows for reviewing items before deletion.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 709]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_2.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_3.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_4.png"
] | 4,408
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Delete all items from cart<image>Thought: Click the DELETE button to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 631]}<image>Thought: Click on the cart icon to access the items in the shopping cart. This allows for reviewing items before deletion.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 709]}<image>",
"role": "user"
},
{
"content": "Thought: I would interpret the message indicating that an item was removed from the Shopping Cart as confirmation of completing the deletion process. This indicates that all items in the cart have been successfully deleted, fulfilling the user's task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_3.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_4.png",
"training_data/AITW/aitw_images/single/13304628969410937822.2257-2307.Delete all items from cart_5.png"
] | 4,409
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Press home button<image>",
"role": "user"
},
{
"content": "Thought: You might want to exit the current Zillow screen to return to the home screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-997.Press home button_0.png"
] | 4,410
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Press home button<image>Thought: You might want to exit the current Zillow screen to return to the home screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press the home button to return to the main screen where all apps are displayed. The task is complete as you are on the home screen now.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17652164182256576003.984-997.Press home button_0.png",
"training_data/AITW/aitw_images/single/17652164182256576003.984-997.Press home button_1.png"
] | 4,411
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to cart<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to quickly access my selected items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 192]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8937124739433252321.446-495.go to cart_0.png"
] | 4,412
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to cart<image>Thought: Click the SHOPPING CART icon to quickly access my selected items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [658, 192]}<image>",
"role": "user"
},
{
"content": "Thought: You accessed the cart page directly, indicating you wanted to view your items.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8937124739433252321.446-495.go to cart_0.png",
"training_data/AITW/aitw_images/single/8937124739433252321.446-495.go to cart_1.png"
] | 4,413
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to chrome search bar and type costco.com <image>",
"role": "user"
},
{
"content": "Thought: You need to click the search bar at the top to input a new URL. Since you clicked on bestbuy.com, you should have access to that search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [272, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _0.png"
] | 4,414
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to chrome search bar and type costco.com <image>Thought: You need to click the search bar at the top to input a new URL. Since you clicked on bestbuy.com, you should have access to that search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [272, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"costco.com\" in the search or type web address field to navigate directly to the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \"costco.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _0.png",
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _1.png"
] | 4,415
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to chrome search bar and type costco.com <image>Thought: You need to click the search bar at the top to input a new URL. Since you clicked on bestbuy.com, you should have access to that search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [272, 73]}<image>Thought: Type \"costco.com\" in the search or type web address field to navigate directly to the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \"costco.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You successfully typed \"costco.com\" into the Chrome search bar, completing the task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _0.png",
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _1.png",
"training_data/AITW/aitw_images/single/8048811742004102307.416-496.go to chrome search bar and type costco.com _2.png"
] | 4,416
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar in ebay.com<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to start entering your search query on eBay.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 268]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16085510022727860642.485-513.Go to the search bar in ebay.com_0.png"
] | 4,417
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar in ebay.com<image>Thought: Click the search bar to start entering your search query on eBay.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 268]}<image>",
"role": "user"
},
{
"content": "Thought: You accessed ebay.com and successfully navigated to the search bar at the top of the page.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/16085510022727860642.485-513.Go to the search bar in ebay.com_0.png",
"training_data/AITW/aitw_images/single/16085510022727860642.485-513.Go to the search bar in ebay.com_1.png"
] | 4,418
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: close the page <image>",
"role": "user"
},
{
"content": "Thought: Click on \"Walmart Official Site - Save with Rollbacks at Walmart\" to open the page and then close it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 394]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _0.png"
] | 4,419
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: close the page <image>Thought: Click on \"Walmart Official Site - Save with Rollbacks at Walmart\" to open the page and then close it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 394]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the current page since it displays an error message.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [21, 62]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _0.png",
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _1.png"
] | 4,420
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: close the page <image>Thought: Click on \"Walmart Official Site - Save with Rollbacks at Walmart\" to open the page and then close it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 394]}<image>Thought: Click the X to close the current page since it displays an error message.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [21, 62]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully closed the page after confirming their intent to leave the current website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _0.png",
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _1.png",
"training_data/AITW/aitw_images/single/2488174016430917617.232-537.close the page _2.png"
] | 4,421
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: choose third suggestion and add to cart <image>",
"role": "user"
},
{
"content": "Thought: Click on the Bluetooth, Wireless Speaker to select the third suggestion from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 491]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _0.png"
] | 4,422
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: choose third suggestion and add to cart <image>Thought: Click on the Bluetooth, Wireless Speaker to select the third suggestion from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 491]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate the third suggestion for selection on the product list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _0.png",
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _1.png"
] | 4,423
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: choose third suggestion and add to cart <image>Thought: Click on the Bluetooth, Wireless Speaker to select the third suggestion from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 491]}<image>Thought: Scroll down to locate the third suggestion for selection on the product list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more product suggestions and find the third option for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _0.png",
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _1.png",
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _2.png"
] | 4,424
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: choose third suggestion and add to cart <image>Thought: Scroll down to locate the third suggestion for selection on the product list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more product suggestions and find the third option for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Select the third suggestion to view its details. Then, find and click the \"Add to Cart\" button for purchase. Confirm that the item has been successfully added to the cart, marking the task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _1.png",
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _2.png",
"training_data/AITW/aitw_images/single/13684417374275856941.563-675.choose third suggestion and add to cart _3.png"
] | 4,425
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for newegg.com in the chrome search bar<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search or type web address\" to start entering the URL for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_0.png"
] | 4,426
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for newegg.com in the chrome search bar<image>Thought: Click on \"Search or type web address\" to start entering the URL for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 70]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" in the Chrome search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" newegg.com.\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_0.png",
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_1.png"
] | 4,427
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for newegg.com in the chrome search bar<image>Thought: Click on \"Search or type web address\" to start entering the URL for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [300, 70]}<image>Thought: Type \"newegg.com\" in the Chrome search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" newegg.com.\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for newegg.com in the Chrome search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_0.png",
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_1.png",
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_2.png"
] | 4,428
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for newegg.com in the chrome search bar<image>Thought: Type \"newegg.com\" in the Chrome search bar to initiate a web search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \" newegg.com.\", \"position\": null}<image>Thought: Press enter to execute the search for newegg.com in the Chrome search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You would indicate task completion as you successfully entered \"newegg.com\" in the search bar.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_1.png",
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_2.png",
"training_data/AITW/aitw_images/single/3131083436876973518.612-848.Search for newegg.com in the chrome search bar_3.png"
] | 4,429
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and enter costco<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to prepare for entering a new search term. Type \"costco\" to perform the desired search query. Press enter to submit the search and view results related to costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 41]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_0.png"
] | 4,430
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and enter costco<image>Thought: Click on the search bar to prepare for entering a new search term. Type \"costco\" to perform the desired search query. Press enter to submit the search and view results related to costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 41]}<image>",
"role": "user"
},
{
"content": "Thought: Tap on the search bar to activate it for typing \"costco\".\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_0.png",
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_1.png"
] | 4,431
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and enter costco<image>Thought: Click on the search bar to prepare for entering a new search term. Type \"costco\" to perform the desired search query. Press enter to submit the search and view results related to costco.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 41]}<image>Thought: Tap on the search bar to activate it for typing \"costco\".\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You would click on the search bar to enter your query. Next, you type \"costco\" in the search bar to look for information. Upon completing the entry and seeing relevant results, you conclude your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_0.png",
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_1.png",
"training_data/AITW/aitw_images/single/4914840023176217498.88-202.Go to search bar and enter costco_2.png"
] | 4,432
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to amazon.com and then go to amazon cart <image>",
"role": "user"
},
{
"content": "Thought: Click on the blue spot to select the link for Amazon.com Shopping Cart. This will take me directly to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 154]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _0.png"
] | 4,433
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to amazon.com and then go to amazon cart <image>Thought: Click on the blue spot to select the link for Amazon.com Shopping Cart. This will take me directly to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 154]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access the items selected for purchase on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [489, 139]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _0.png",
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _1.png"
] | 4,434
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to amazon.com and then go to amazon cart <image>Thought: Click on the blue spot to select the link for Amazon.com Shopping Cart. This will take me directly to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [234, 154]}<image>Thought: Click the SHOPPING CART to access the items selected for purchase on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [489, 139]}<image>",
"role": "user"
},
{
"content": "Thought: The user navigated to amazon.com to access their cart, confirming they completed their task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _0.png",
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _1.png",
"training_data/AITW/aitw_images/single/17809171743554211783.161-219.go to amazon.com and then go to amazon cart _2.png"
] | 4,435
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>",
"role": "user"
},
{
"content": "Thought: Click the Search button to initiate a search for the Logitech G903 on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 258]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_0.png"
] | 4,436
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>Thought: Click the Search button to initiate a search for the Logitech G903 on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 258]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g90\" in the search box to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g90\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_0.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_1.png"
] | 4,437
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>Thought: Click the Search button to initiate a search for the Logitech G903 on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 258]}<image>Thought: Type \"logitech g90\" in the search box to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g90\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to begin searching for the Logitech G903.\nAction: {\"action\": \"TYPE\", \"value\": \"3\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_0.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_1.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_2.png"
] | 4,438
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>Thought: Type \"logitech g90\" in the search box to find relevant products.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g90\", \"position\": null}<image>Thought: Type in the search bar to begin searching for the Logitech G903.\nAction: {\"action\": \"TYPE\", \"value\": \"3\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g903\" in the search bar to find the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_1.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_2.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_3.png"
] | 4,439
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>Thought: Type in the search bar to begin searching for the Logitech G903.\nAction: {\"action\": \"TYPE\", \"value\": \"3\", \"position\": null}<image>Thought: Type \"logitech g903\" in the search bar to find the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"logitech g203\" since it is a suggestion in the search results dropdown.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [153, 265]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_2.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_3.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_4.png"
] | 4,440
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for logitech g903 on bestbuy.com<image>Thought: Type \"logitech g903\" in the search bar to find the product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Click on \"logitech g203\" since it is a suggestion in the search results dropdown.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [153, 265]}<image>",
"role": "user"
},
{
"content": "Thought: Confirm that the search for \"logitech g903\" was successful because the results page shows related products.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_3.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_4.png",
"training_data/AITW/aitw_images/single/9053135248670407006.592-1032.search for logitech g903 on bestbuy.com_5.png"
] | 4,441
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to logitech g pro <image>",
"role": "user"
},
{
"content": "Thought: Click on \"logitech g pro\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 117]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13110457603793348272.939-991.go to logitech g pro _0.png"
] | 4,442
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: go to logitech g pro <image>Thought: Click on \"logitech g pro\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 117]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully found the search results for \"logitech g pro\" in the GUI.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13110457603793348272.939-991.go to logitech g pro _0.png",
"training_data/AITW/aitw_images/single/13110457603793348272.939-991.go to logitech g pro _1.png"
] | 4,443
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to chrome search bar and search for amazon<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon\" in the Chrome search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_0.png"
] | 4,444
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to chrome search bar and search for amazon<image>Thought: Type \"amazon\" in the Chrome search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon.com to quickly access the website directly from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 135]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_0.png",
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_1.png"
] | 4,445
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to chrome search bar and search for amazon<image>Thought: Type \"amazon\" in the Chrome search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>Thought: Click on Amazon.com to quickly access the website directly from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 135]}<image>",
"role": "user"
},
{
"content": "Thought: You entered \"amazon\" in the Chrome search bar to find information about Amazon. Your search yielded results related to Amazon, indicating a successful search operation. The task is complete as you successfully searched for the desired term in Chrome.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_0.png",
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_1.png",
"training_data/AITW/aitw_images/single/15689901867044049466.1662-1704.Go to chrome search bar and search for amazon_2.png"
] | 4,446
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to newegg search bar and search for razer deathadder<image>",
"role": "user"
},
{
"content": "Thought: Click on the DEALS section to find potential discounts on the Razer DeathAdder.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 186]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_0.png"
] | 4,447
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to newegg search bar and search for razer deathadder<image>Thought: Click on the DEALS section to find potential discounts on the Razer DeathAdder.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 186]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer deathadder\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer deathadder\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_0.png",
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_1.png"
] | 4,448
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to newegg search bar and search for razer deathadder<image>Thought: Click on the DEALS section to find potential discounts on the Razer DeathAdder.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [340, 186]}<image>Thought: Type \"razer deathadder\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer deathadder\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter on the search bar to execute the search for \"razer deathadder\".\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_0.png",
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_1.png",
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_2.png"
] | 4,449
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to newegg search bar and search for razer deathadder<image>Thought: Type \"razer deathadder\" in the search bar to initiate the product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer deathadder\", \"position\": null}<image>Thought: Press enter on the search bar to execute the search for \"razer deathadder\".\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed the newegg search bar and entered \"razer deathadder,\" yielding the relevant search results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_1.png",
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_2.png",
"training_data/AITW/aitw_images/single/12915037436835775879.347-641.Go to newegg search bar and search for razer deathadder_3.png"
] | 4,450
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show all apps<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more apps available in the app drawer.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1467588501861042414.889-933.Show all apps_0.png"
] | 4,451
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show all apps<image>Thought: Scroll down to see more apps available in the app drawer.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed and viewed all apps displayed on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1467588501861042414.889-933.Show all apps_0.png",
"training_data/AITW/aitw_images/single/1467588501861042414.889-933.Show all apps_1.png"
] | 4,452
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar on bestbuy.com and search for usb-a<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar at the top of the page to enter your query for \"usb-a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [242, 176]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_0.png"
] | 4,453
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar on bestbuy.com and search for usb-a<image>Thought: Click the search bar at the top of the page to enter your query for \"usb-a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [242, 176]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"usb-a\" in the search bar to find related products on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_0.png",
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_1.png"
] | 4,454
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar on bestbuy.com and search for usb-a<image>Thought: Click the search bar at the top of the page to enter your query for \"usb-a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [242, 176]}<image>Thought: Type \"usb-a\" in the search bar to find related products on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for usb-a in the search bar on bestbuy.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_0.png",
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_1.png",
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_2.png"
] | 4,455
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the search bar on bestbuy.com and search for usb-a<image>Thought: Type \"usb-a\" in the search bar to find related products on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}<image>Thought: Press enter to execute the search for usb-a in the search bar on bestbuy.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task by successfully locating the search bar on bestbuy.com and searching for \"usb-a.\"\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_1.png",
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_2.png",
"training_data/AITW/aitw_images/single/13790613883690656585.879-987.Go to the search bar on bestbuy.com and search for usb-a_3.png"
] | 4,456
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on newegg.com<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer huntsman\" in the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_0.png"
] | 4,457
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on newegg.com<image>Thought: Type \"razer huntsman\" in the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"razer huntsman\" to select the specific product from search results and view more details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 193]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_0.png",
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_1.png"
] | 4,458
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on newegg.com<image>Thought: Type \"razer huntsman\" in the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>Thought: Click on \"razer huntsman\" to select the specific product from search results and view more details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 193]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully completed the search for \"razer huntsman\" on Newegg, evidenced by 23 search results displayed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_0.png",
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_1.png",
"training_data/AITW/aitw_images/single/7005961376513612887.773-878.Search for razer huntsman on newegg.com_2.png"
] | 4,459
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the tab section and then go to second tab<image>",
"role": "user"
},
{
"content": "Thought: Click the ARROW UPWARD to navigate towards the tab section at the top of the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 84]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_0.png"
] | 4,460
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the tab section and then go to second tab<image>Thought: Click the ARROW UPWARD to navigate towards the tab section at the top of the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 84]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Already a customer?\" option to access the sign-in page for Amazon. This indicates you want to authenticate your account.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [527, 345]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_0.png",
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_1.png"
] | 4,461
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the tab section and then go to second tab<image>Thought: Click the ARROW UPWARD to navigate towards the tab section at the top of the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 84]}<image>Thought: Click the \"Already a customer?\" option to access the sign-in page for Amazon. This indicates you want to authenticate your account.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [527, 345]}<image>",
"role": "user"
},
{
"content": "Thought: You completed the task by accessing the desired tab section and navigating to the second tab, confirming your goal was achieved.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_0.png",
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_1.png",
"training_data/AITW/aitw_images/single/14373117290050675889.652-687.Go to the tab section and then go to second tab_2.png"
] | 4,462
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to Walmart website<image>",
"role": "user"
},
{
"content": "Thought: Click on the Walmart link because it is the direct access to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [97, 124]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_0.png"
] | 4,463
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to Walmart website<image>Thought: Click on the Walmart link because it is the direct access to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [97, 124]}<image>",
"role": "user"
},
{
"content": "Thought: Click Walmart to access the official Walmart website from the search results displayed on Google.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 339]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_0.png",
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_1.png"
] | 4,464
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to Walmart website<image>Thought: Click on the Walmart link because it is the direct access to the Walmart website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [97, 124]}<image>Thought: Click Walmart to access the official Walmart website from the search results displayed on Google.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 339]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully accessed the Walmart website, fulfilling their task. The visible elements confirm the website is loaded and functional.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_0.png",
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_1.png",
"training_data/AITW/aitw_images/single/9365954963403258244.162-313.Go to Walmart website_2.png"
] | 4,465
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: select the first result and add to cart<image>",
"role": "user"
},
{
"content": "Thought: Click the STAR to highlight the first result for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 815]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_0.png"
] | 4,466
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: select the first result and add to cart<image>Thought: Click the STAR to highlight the first result for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 815]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the full list of search results and find the first item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_0.png",
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_1.png"
] | 4,467
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: select the first result and add to cart<image>Thought: Click the STAR to highlight the first result for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 815]}<image>Thought: Scroll down to view the full list of search results and find the first item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'Add to Cart' button to select the first result and proceed with purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 1310]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_0.png",
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_1.png",
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_2.png"
] | 4,468
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: select the first result and add to cart<image>Thought: Scroll down to view the full list of search results and find the first item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the 'Add to Cart' button to select the first result and proceed with purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 1310]}<image>",
"role": "user"
},
{
"content": "Thought: The task is marked as complete because the user successfully added the first result to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_1.png",
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_2.png",
"training_data/AITW/aitw_images/single/17715444826853563573.435-553.select the first result and add to cart_3.png"
] | 4,469
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result and go to cart section, then Add to cart<image>",
"role": "user"
},
{
"content": "Thought: Click on the highlighted \"Intel\" link to view more details about the product. Scroll down or navigate to find the cart section. Click on \"Add to cart\" for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 826]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_0.png"
] | 4,470
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result and go to cart section, then Add to cart<image>Thought: Click on the highlighted \"Intel\" link to view more details about the product. Scroll down or navigate to find the cart section. Click on \"Add to cart\" for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 826]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the first result for the ASUS ZenBook Duo.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_0.png",
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_1.png"
] | 4,471
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result and go to cart section, then Add to cart<image>Thought: Click on the highlighted \"Intel\" link to view more details about the product. Scroll down or navigate to find the cart section. Click on \"Add to cart\" for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 826]}<image>Thought: Scroll down to view the first result for the ASUS ZenBook Duo.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Add to Cart to save the item for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [294, 954]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_0.png",
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_1.png",
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_2.png"
] | 4,472
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open first result and go to cart section, then Add to cart<image>Thought: Scroll down to view the first result for the ASUS ZenBook Duo.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click Add to Cart to save the item for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [294, 954]}<image>",
"role": "user"
},
{
"content": "Thought: The user likely clicked on the first result to view the product details. The user then navigated to the cart section to manage their items. Finally, they added the item to the cart, completing their purchasing task successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_1.png",
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_2.png",
"training_data/AITW/aitw_images/single/17756103836707148197.1169-1371.Open first result and go to cart section, then Add to cart_3.png"
] | 4,473
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the chrome search bar and then go to walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to enter a new URL. Type \"walmart.com\" into the search bar for navigation. Press enter to initiate the search and load Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 57]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_0.png"
] | 4,474
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the chrome search bar and then go to walmart.com<image>Thought: Click on the search bar to enter a new URL. Type \"walmart.com\" into the search bar for navigation. Press enter to initiate the search and load Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 57]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Walmart.com\" in the chrome search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_0.png",
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_1.png"
] | 4,475
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the chrome search bar and then go to walmart.com<image>Thought: Click on the search bar to enter a new URL. Type \"walmart.com\" into the search bar for navigation. Press enter to initiate the search and load Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 57]}<image>Thought: Type \"Walmart.com\" in the chrome search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the suggestion for walmart.com to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 145]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_0.png",
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_1.png",
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_2.png"
] | 4,476
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to the chrome search bar and then go to walmart.com<image>Thought: Type \"Walmart.com\" in the chrome search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Walmart.com\", \"position\": null}<image>Thought: Click the suggestion for walmart.com to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [201, 145]}<image>",
"role": "user"
},
{
"content": "Thought: You have accessed the Chrome search bar and successfully navigated to walmart.com, completing your task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_1.png",
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_2.png",
"training_data/AITW/aitw_images/single/9572749773230895261.308-450.Go to the chrome search bar and then go to walmart.com_3.png"
] | 4,477
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and search newegg.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to input a new search term. Type \"newegg.com\" to perform the desired search. Press enter to execute the search for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 114]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_0.png"
] | 4,478
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and search newegg.com<image>Thought: Click on the search bar to input a new search term. Type \"newegg.com\" to perform the desired search. Press enter to execute the search for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 114]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" in the search bar to navigate directly to the website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_0.png",
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_1.png"
] | 4,479
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and search newegg.com<image>Thought: Click on the search bar to input a new search term. Type \"newegg.com\" to perform the desired search. Press enter to execute the search for newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 114]}<image>Thought: Type \"newegg.com\" in the search bar to navigate directly to the website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the newegg.com suggestion in the search bar to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 336]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_0.png",
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_1.png",
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_2.png"
] | 4,480
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Go to search bar and search newegg.com<image>Thought: Type \"newegg.com\" in the search bar to navigate directly to the website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Click the newegg.com suggestion in the search bar to quickly access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 336]}<image>",
"role": "user"
},
{
"content": "Thought: You accessed the search bar on Google to input \"newegg.com.\" The status task complete indicates you successfully found and searched for newegg.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_1.png",
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_2.png",
"training_data/AITW/aitw_images/single/1716244737885862460.191-404.Go to search bar and search newegg.com_3.png"
] | 4,481
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add to cart \"24pc panasonic AAA batteries\"<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add\" button to add the 24pc Panasonic AAA batteries to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 690]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17585541886958895731.1069-1106.Add to cart \"24pc panasonic AAA batteries\"_0.png"
] | 4,482
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add to cart \"24pc panasonic AAA batteries\"<image>Thought: Click the \"Add\" button to add the 24pc Panasonic AAA batteries to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 690]}<image>",
"role": "user"
},
{
"content": "Thought: You would have clicked the \"Add\" button on the battery product to include it in your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/17585541886958895731.1069-1106.Add to cart \"24pc panasonic AAA batteries\"_0.png",
"training_data/AITW/aitw_images/single/17585541886958895731.1069-1106.Add to cart \"24pc panasonic AAA batteries\"_1.png"
] | 4,483
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open the second search result on newegg.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the second search result for Apple AirPods Pro to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 500]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12811985773245238740.571-842.Open the second search result on newegg.com_0.png"
] | 4,484
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open the second search result on newegg.com<image>Thought: Click on the second search result for Apple AirPods Pro to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 500]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully opened the second search result, which is displayed, indicating task completion.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/12811985773245238740.571-842.Open the second search result on newegg.com_0.png",
"training_data/AITW/aitw_images/single/12811985773245238740.571-842.Open the second search result on newegg.com_1.png"
] | 4,485
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>",
"role": "user"
},
{
"content": "Thought: Click the blue spot to access the search bar for typing. Type \"costco.com\" to initiate your search. Press enter to confirm the web address. Now, utilize the search bar again for searching \"asus zenbook.\" Press enter once more to complete your search request.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 323]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_0.png"
] | 4,486
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click the blue spot to access the search bar for typing. Type \"costco.com\" to initiate your search. Press enter to confirm the web address. Now, utilize the search bar again for searching \"asus zenbook.\" Press enter once more to complete your search request.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 323]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"costco\" in the search bar to initiate a web search for Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_0.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_1.png"
] | 4,487
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click the blue spot to access the search bar for typing. Type \"costco.com\" to initiate your search. Press enter to confirm the web address. Now, utilize the search bar again for searching \"asus zenbook.\" Press enter once more to complete your search request.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 323]}<image>Thought: Type \"costco\" in the search bar to initiate a web search for Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Costco\" to access the Costco website for further search options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 202]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_0.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_1.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_2.png"
] | 4,488
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Type \"costco\" in the search bar to initiate a web search for Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>Thought: Click on \"Costco\" to access the Costco website for further search options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 202]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for asus zenbook.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 205]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_1.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_2.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_3.png"
] | 4,489
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click on \"Costco\" to access the Costco website for further search options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [83, 202]}<image>Thought: Click the magnifying glass to initiate a search for asus zenbook.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 205]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to clear the existing search term \"costco\" from the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 122]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_2.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_3.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_4.png"
] | 4,490
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click the magnifying glass to initiate a search for asus zenbook.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 205]}<image>Thought: Click the X to clear the existing search term \"costco\" from the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 122]}<image>",
"role": "user"
},
{
"content": "Thought: Click Costco to select it from the search results for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 188]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_3.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_4.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_5.png"
] | 4,491
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click the X to clear the existing search term \"costco\" from the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 122]}<image>Thought: Click Costco to select it from the search results for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 188]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco Wholesale link to navigate to the website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 377]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_4.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_5.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_6.png"
] | 4,492
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click Costco to select it from the search results for further action.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 188]}<image>Thought: Click on the Costco Wholesale link to navigate to the website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 377]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Warehouses\" to navigate to the appropriate section for product availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [285, 190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_5.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_6.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_7.png"
] | 4,493
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click on the Costco Wholesale link to navigate to the website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 377]}<image>Thought: Click on \"Warehouses\" to navigate to the appropriate section for product availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [285, 190]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"asus zenbook\" in the search bar to find specific products.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_6.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_7.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_8.png"
] | 4,494
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Click on \"Warehouses\" to navigate to the appropriate section for product availability.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [285, 190]}<image>Thought: Type \"asus zenbook\" in the search bar to find specific products.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"asus\" in the search suggestions to view more related options for asus zenbook.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 242]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_7.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_8.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_9.png"
] | 4,495
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: search for costco.com then go to search bar and search for asus zenbook<image>Thought: Type \"asus zenbook\" in the search bar to find specific products.\nAction: {\"action\": \"TYPE\", \"value\": \"asus zenbook\", \"position\": null}<image>Thought: Click on \"asus\" in the search suggestions to view more related options for asus zenbook.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 242]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete because the search for \"asus zenbook\" yielded results on Costco's website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_8.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_9.png",
"training_data/AITW/aitw_images/single/13792752501542986537.89-366.search for costco.com then go to search bar and search for asus zenbook_10.png"
] | 4,496
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search and open amazon.com on google chrome<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" in the search bar to access the Amazon website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_0.png"
] | 4,497
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search and open amazon.com on google chrome<image>Thought: Type \"amazon.com\" in the search bar to access the Amazon website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on amazon.com to open the website directly from the search results in Google Chrome.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 192]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_0.png",
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_1.png"
] | 4,498
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search and open amazon.com on google chrome<image>Thought: Type \"amazon.com\" in the search bar to access the Amazon website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Click on amazon.com to open the website directly from the search results in Google Chrome.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 192]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully opened amazon.com in Google Chrome, fulfilling your search task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_0.png",
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_1.png",
"training_data/AITW/aitw_images/single/8984466072995370188.1373-1598.Search and open amazon.com on google chrome_2.png"
] | 4,499
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.