messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Press enter to select the autocomplete suggestion for \"macbook pro 13 inch\" in the search box.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view product options and search results for the MacBook Pro 13 inch on Costco.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products and find the MacBook Pro 13 inch.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_8.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_9.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_10.png"
] | 10,100
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view product options and search results for the MacBook Pro 13 inch on Costco.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products and find the MacBook Pro 13 inch.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the MacBook Pro option to view its details. Then click on the \"Add\" button to include it in your shopping cart. After that, proceed by selecting the checkout option.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 490]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_9.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_10.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_11.png"
] | 10,101
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view more products and find the MacBook Pro 13 inch.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the MacBook Pro option to view its details. Then click on the \"Add\" button to include it in your shopping cart. After that, proceed by selecting the checkout option.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 490]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the MacBook Pro 13-inch details and access the add-to-cart option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_10.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_11.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_12.png"
] | 10,102
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Click on the MacBook Pro option to view its details. Then click on the \"Add\" button to include it in your shopping cart. After that, proceed by selecting the checkout option.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 490]}<image>Thought: Scroll down to view the MacBook Pro 13-inch details and access the add-to-cart option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the product details and add it to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_11.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_12.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_13.png"
] | 10,103
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view the MacBook Pro 13-inch details and access the add-to-cart option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the product details and add it to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see the shopping cart icon and checkout options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_12.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_13.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_14.png"
] | 10,104
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view the product details and add it to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see the shopping cart icon and checkout options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the MacBook Pro and ensure it's added to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_13.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_14.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_15.png"
] | 10,105
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to see the shopping cart icon and checkout options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the MacBook Pro and ensure it's added to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'Add to Cart' button to include the MacBook Pro in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 535]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_14.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_15.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_16.png"
] | 10,106
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view more details about the MacBook Pro and ensure it's added to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the 'Add to Cart' button to include the MacBook Pro in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 535]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"View Cart\" button to quickly access the shopping cart and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 447]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_15.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_16.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_17.png"
] | 10,107
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Click the 'Add to Cart' button to include the MacBook Pro in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 535]}<image>Thought: Click the \"View Cart\" button to quickly access the shopping cart and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 447]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Checkout button to proceed with the purchase of items in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 639]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_16.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_17.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_18.png"
] | 10,108
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on costco.com. Add macbook pro 13 inch to the cart on costco.com, then select checkout.<image>Thought: Click the \"View Cart\" button to quickly access the shopping cart and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 447]}<image>Thought: Click the Checkout button to proceed with the purchase of items in my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 639]}<image>",
"role": "user"
},
{
"content": "Thought: You are currently signed in to Costco. Since you wanted to show the shopping cart, navigate through the site to access it. Next, select the MacBook Pro 13 inch and add it to your cart. Finally, proceed with selecting checkout because you've completed adding items to your cart successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1635576072551962337_17.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_18.png",
"training_data/AITW/aitw_images/webshopping/1635576072551962337_19.png"
] | 10,109
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [232, 957]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_0.png"
] | 10,110
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [232, 957]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"costco\" to search for Costco's website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_0.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_1.png"
] | 10,111
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Chrome icon to open the web browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [232, 957]}<image>Thought: Type \"costco\" to search for Costco's website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"costco.com\" to access the website and perform the shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 251]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_0.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_1.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_2.png"
] | 10,112
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"costco\" to search for Costco's website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>Thought: Click on \"costco.com\" to access the website and perform the shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 251]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Costco\" to access the Costco website for further shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 355]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_1.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_2.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_3.png"
] | 10,113
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"costco.com\" to access the website and perform the shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [279, 251]}<image>Thought: Click on \"Costco\" to access the Costco website for further shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 355]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Shop\" section to access product categories for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 188]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_2.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_3.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_4.png"
] | 10,114
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on \"Costco\" to access the Costco website for further shopping actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 355]}<image>Thought: Click on the \"Shop\" section to access product categories for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 188]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"lenovo thinkpad\" in the search bar to find related products on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_3.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_4.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_5.png"
] | 10,115
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the \"Shop\" section to access product categories for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 188]}<image>Thought: Type \"lenovo thinkpad\" in the search bar to find related products on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for Lenovo Thinkpad on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [483, 185]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_4.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_5.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_6.png"
] | 10,116
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"lenovo thinkpad\" in the search bar to find related products on costco.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lenovo thinkpad\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for Lenovo Thinkpad on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [483, 185]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked \"Add\" to place the selected Lenovo ThinkPad into your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 891]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_5.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_6.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_7.png"
] | 10,117
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on costco.com. Search for lenovo thinkpad on costco.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the magnifying glass to initiate a search for Lenovo Thinkpad on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [483, 185]}<image>Thought: You clicked \"Add\" to place the selected Lenovo ThinkPad into your shopping cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 891]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that the search led to a list where the Lenovo Thinkpad was not found but products were displayed. Acknowledge the presence of a related product, indicating an interest in purchasing. Select to add the first displayed item, validating it as an alternative for checkout. Proceed by clicking on 'Add' for that item directly from its listing efficiently leading to cart preparation. Conclude with status task complete as all intended steps have been fulfilled despite deviations from original search expectation.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13570107860498789779_6.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_7.png",
"training_data/AITW/aitw_images/webshopping/13570107860498789779_8.png"
] | 10,118
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to access the app drawer where I can find the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 1365]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_0.png"
] | 10,119
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click the NAV BAR CIRCLE to access the app drawer where I can find the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 1365]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target\" to find the Target app from the search suggestions.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_0.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_1.png"
] | 10,120
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click the NAV BAR CIRCLE to access the app drawer where I can find the Target app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [316, 1365]}<image>Thought: Type \"target\" to find the Target app from the search suggestions.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"target hours\" option to access the Target store information for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 423]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_0.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_1.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_2.png"
] | 10,121
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Type \"target\" to find the Target app from the search suggestions.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>Thought: Click the \"target hours\" option to access the Target store information for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 423]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Official\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 667]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_1.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_2.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_3.png"
] | 10,122
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click the \"target hours\" option to access the Target store information for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 423]}<image>Thought: Click the \"Official\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 667]}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to find the \"logitech g903\" in the Target app or website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 407]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_2.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_3.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_4.png"
] | 10,123
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click the \"Official\" link to navigate to the Target website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 667]}<image>Thought: Click Search to find the \"logitech g903\" in the Target app or website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 407]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g903\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_3.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_4.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_5.png"
] | 10,124
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click Search to find the \"logitech g903\" in the Target app or website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 407]}<image>Thought: Type \"logitech g903\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to execute the search for \"logitech g903\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_4.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_5.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_6.png"
] | 10,125
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Type \"logitech g903\" in the search bar to find the product on Target's website.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g903\", \"position\": null}<image>Thought: Click the magnifying glass to execute the search for \"logitech g903\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 225]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to \"logitech g903\" to find the purchase option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_5.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_6.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_7.png"
] | 10,126
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Click the magnifying glass to execute the search for \"logitech g903\" on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 225]}<image>Thought: Scroll down to view more products related to \"logitech g903\" to find the purchase option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to successfully add the \"logitech g903\" item from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [528, 828]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_6.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_7.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_8.png"
] | 10,127
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"logitech g903\" to the cart on target, then select checkout.<image>Thought: Scroll down to view more products related to \"logitech g903\" to find the purchase option.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to successfully add the \"logitech g903\" item from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [528, 828]}<image>",
"role": "user"
},
{
"content": "Thought: Verify that \"logitech g903\" appears in the search results and click its \"Add to cart\" button. Then, confirm the cart is updated and proceed to checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/481926593068847470_7.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_8.png",
"training_data/AITW/aitw_images/webshopping/481926593068847470_9.png"
] | 10,128
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>",
"role": "user"
},
{
"content": "Thought: Click the CHAT app to possibly ask for book recommendations or search assistance on Goodreads.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 522]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_0.png"
] | 10,129
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the CHAT app to possibly ask for book recommendations or search assistance on Goodreads.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 522]}<image>",
"role": "user"
},
{
"content": "Thought: Click the THREE DOTS to access more options for refining your search or navigating further.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_0.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_1.png"
] | 10,130
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the CHAT app to possibly ask for book recommendations or search assistance on Goodreads.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 522]}<image>Thought: Click the THREE DOTS to access more options for refining your search or navigating further.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find relevant search results for fantasy books on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_0.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_1.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_2.png"
] | 10,131
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the THREE DOTS to access more options for refining your search or navigating further.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 67]}<image>Thought: Scroll down to find relevant search results for fantasy books on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to access the search bar of a previous tab for finding fantasy books.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_1.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_2.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_3.png"
] | 10,132
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Scroll down to find relevant search results for fantasy books on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to access the search bar of a previous tab for finding fantasy books.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view more tabs in the browser and locate the Goodreads tab for book searching.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_2.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_3.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_4.png"
] | 10,133
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Scroll up to access the search bar of a previous tab for finding fantasy books.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view more tabs in the browser and locate the Goodreads tab for book searching.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Goodreads link to access the website for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 222]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_3.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_4.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_5.png"
] | 10,134
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Scroll up to view more tabs in the browser and locate the Goodreads tab for book searching.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click the Goodreads link to access the website for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 222]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search function for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 286]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_4.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_5.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_6.png"
] | 10,135
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the Goodreads link to access the website for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 222]}<image>Thought: Click the magnifying glass to initiate the search function for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 286]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Search books\" entry field to prepare for typing my search query for fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 351]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_5.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_6.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_7.png"
] | 10,136
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the magnifying glass to initiate the search function for finding fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 286]}<image>Thought: Click on the \"Search books\" entry field to prepare for typing my search query for fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 351]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"best fantasy books\" in the search bar to look for relevant titles on Goodreads.\nAction: {\"action\": \"TYPE\", \"value\": \"best fantasy books \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_6.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_7.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_8.png"
] | 10,137
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click on the \"Search books\" entry field to prepare for typing my search query for fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 351]}<image>Thought: Type \"best fantasy books\" in the search bar to look for relevant titles on Goodreads.\nAction: {\"action\": \"TYPE\", \"value\": \"best fantasy books \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"best fantasy books\" on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_7.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_8.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_9.png"
] | 10,138
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Type \"best fantasy books\" in the search bar to look for relevant titles on Goodreads.\nAction: {\"action\": \"TYPE\", \"value\": \"best fantasy books \", \"position\": null}<image>Thought: Scroll down to view more search results for \"best fantasy books\" on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to see more fantasy book recommendations on the Goodreads search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_8.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_9.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_10.png"
] | 10,139
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Scroll down to view more search results for \"best fantasy books\" on Goodreads.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to see more fantasy book recommendations on the Goodreads search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click X to clear the current search term in the input box and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 126]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_9.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_10.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_11.png"
] | 10,140
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Scroll up to see more fantasy book recommendations on the Goodreads search results.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click X to clear the current search term in the input box and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 126]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Goodreads search bar to focus on it for typing. Type \"best fantasy books\" to specify your search query. Press enter to execute the search and retrieve results for best fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 249]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_10.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_11.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_12.png"
] | 10,141
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click X to clear the current search term in the input box and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 126]}<image>Thought: Click the Goodreads search bar to focus on it for typing. Type \"best fantasy books\" to specify your search query. Press enter to execute the search and retrieve results for best fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 249]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"See all results for 'best fantasy books'\" button to view a comprehensive list of related books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [203, 660]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_11.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_12.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_13.png"
] | 10,142
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the Goodreads search bar to focus on it for typing. Type \"best fantasy books\" to specify your search query. Press enter to execute the search and retrieve results for best fantasy books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 249]}<image>Thought: Click the \"See all results for 'best fantasy books'\" button to view a comprehensive list of related books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [203, 660]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the results for \"best fantasy books\" to view more details about the recommended titles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 665]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_12.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_13.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_14.png"
] | 10,143
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click the \"See all results for 'best fantasy books'\" button to view a comprehensive list of related books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [203, 660]}<image>Thought: Click on the results for \"best fantasy books\" to view more details about the recommended titles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 665]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"X\" to close the sign-up prompt and access the search bar for books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 217]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_13.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_14.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_15.png"
] | 10,144
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for the best fantasy books on Goodreads.<image>Thought: Click on the results for \"best fantasy books\" to view more details about the recommended titles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 665]}<image>Thought: Click the \"X\" to close the sign-up prompt and access the search bar for books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [388, 217]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully searched for the best fantasy books on Goodreads, as indicated by the displayed results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6821846183204919720_14.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_15.png",
"training_data/AITW/aitw_images/webshopping/6821846183204919720_16.png"
] | 10,145
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current Messages app and return to the main screen for better navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_0.png"
] | 10,146
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Press home to exit the current Messages app and return to the main screen for better navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to access notifications, then navigate to Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1139]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_0.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_1.png"
] | 10,147
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Press home to exit the current Messages app and return to the main screen for better navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the ENVELOPE to access notifications, then navigate to Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1139]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the URL to access your shopping cart. You need to authenticate to view your cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 75]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_0.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_1.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_2.png"
] | 10,148
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click the ENVELOPE to access notifications, then navigate to Walmart for your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1139]}<image>Thought: Click on the URL to access your shopping cart. You need to authenticate to view your cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 75]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" in the search bar to navigate to the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_1.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_2.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_3.png"
] | 10,149
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click on the URL to access your shopping cart. You need to authenticate to view your cart contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [315, 75]}<image>Thought: Type \"walmart\" in the search bar to navigate to the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Walmart to access the Walmart website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 278]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_2.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_3.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_4.png"
] | 10,150
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Type \"walmart\" in the search bar to navigate to the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click Walmart to access the Walmart website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 278]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Walmart.com to navigate to the shopping site and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [217, 600]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_3.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_4.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_5.png"
] | 10,151
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click Walmart to access the Walmart website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 278]}<image>Thought: Click on Walmart.com to navigate to the shopping site and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [217, 600]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to enter \"acer nitro\" for the shopping cart task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [401, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_4.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_5.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_6.png"
] | 10,152
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click on Walmart.com to navigate to the shopping site and access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [217, 600]}<image>Thought: Click on the search bar to enter \"acer nitro\" for the shopping cart task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [401, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer nitro\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_5.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_6.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_7.png"
] | 10,153
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click on the search bar to enter \"acer nitro\" for the shopping cart task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [401, 184]}<image>Thought: Type \"acer nitro\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to initiate a search for \"acer nitro\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [580, 177]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_6.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_7.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_8.png"
] | 10,154
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Type \"acer nitro\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>Thought: Click the MAGNIFYING GLASS to initiate a search for \"acer nitro\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [580, 177]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Acer Nitro 5, 15.6\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 733]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_7.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_8.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_9.png"
] | 10,155
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click the MAGNIFYING GLASS to initiate a search for \"acer nitro\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [580, 177]}<image>Thought: Click on the Acer Nitro 5, 15.6\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 733]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to add the Acer Nitro 5 to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 1316]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_8.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_9.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_10.png"
] | 10,156
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click on the Acer Nitro 5, 15.6\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 733]}<image>Thought: Click the \"Add to cart\" button to add the Acer Nitro 5 to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 1316]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Decline\" to dismiss the protection plan offer and continue viewing the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 1315]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_9.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_10.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_11.png"
] | 10,157
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on walmart. Add \"acer nitro\" to the cart on walmart<image>Thought: Click the \"Add to cart\" button to add the Acer Nitro 5 to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [607, 1316]}<image>Thought: Click \"Decline\" to dismiss the protection plan offer and continue viewing the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 1315]}<image>",
"role": "user"
},
{
"content": "Thought: Check the cart confirmation to verify \"acer nitro\" was added successfully. The GUI displays \"Added to cart!\" confirmation.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/292705044226933930_10.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_11.png",
"training_data/AITW/aitw_images/webshopping/292705044226933930_12.png"
] | 10,158
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_0.png"
] | 10,159
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app and proceed with browsing Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 910]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_0.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_1.png"
] | 10,160
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click PLAY to open the app and proceed with browsing Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 910]}<image>",
"role": "user"
},
{
"content": "Thought: Search for \"Razer Blade\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [207, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_0.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_1.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_2.png"
] | 10,161
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click PLAY to open the app and proceed with browsing Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 910]}<image>Thought: Search for \"Razer Blade\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [207, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" to navigate to the Amazon website for purchasing.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_1.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_2.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_3.png"
] | 10,162
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Search for \"Razer Blade\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [207, 73]}<image>Thought: Type \"amazon.com\" to navigate to the Amazon website for purchasing.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"amazon.com\" to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 243]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_2.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_3.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_4.png"
] | 10,163
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Type \"amazon.com\" to navigate to the Amazon website for purchasing.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Click on \"amazon.com\" to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 243]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the link for Amazon.com since it's necessary to access the website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_3.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_4.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_5.png"
] | 10,164
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click on \"amazon.com\" to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [176, 243]}<image>Thought: Scroll down to find the link for Amazon.com since it's necessary to access the website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon Home & Kitchen link to navigate to a relevant section for searching products like Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 687]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_4.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_5.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_6.png"
] | 10,165
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Scroll down to find the link for Amazon.com since it's necessary to access the website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Amazon Home & Kitchen link to navigate to a relevant section for searching products like Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 687]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Basics\" to explore the category where the razer blade may be listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [267, 227]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_5.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_6.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_7.png"
] | 10,166
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click the Amazon Home & Kitchen link to navigate to a relevant section for searching products like Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 687]}<image>Thought: Click on \"Basics\" to explore the category where the razer blade may be listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [267, 227]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_6.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_7.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_8.png"
] | 10,167
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click on \"Basics\" to explore the category where the razer blade may be listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [267, 227]}<image>Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"razer blade\" suggestion to quickly access the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 369]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_7.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_8.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_9.png"
] | 10,168
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>Thought: Click the \"razer blade\" suggestion to quickly access the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 369]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Razer Blade entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 1020]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_8.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_9.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_10.png"
] | 10,169
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click the \"razer blade\" suggestion to quickly access the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [103, 369]}<image>Thought: Click on the Razer Blade entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 1020]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Razer Blade gaming laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_9.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_10.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_11.png"
] | 10,170
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Click on the Razer Blade entry to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 1020]}<image>Thought: Scroll down to view more details about the Razer Blade gaming laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to access the \"Add to Cart\" button, as it is located lower on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_10.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_11.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_12.png"
] | 10,171
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Scroll down to view more details about the Razer Blade gaming laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to access the \"Add to Cart\" button, as it is located lower on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include the Razer Blade in your shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [265, 695]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_11.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_12.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_13.png"
] | 10,172
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer blade to the cart on amazon.com<image>Thought: Scroll down to access the \"Add to Cart\" button, as it is located lower on the page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to include the Razer Blade in your shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [265, 695]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the user has successfully added the Razer Blade to their cart, reflected in the subtotal.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16558212226998514179_12.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_13.png",
"training_data/AITW/aitw_images/webshopping/16558212226998514179_14.png"
] | 10,173
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>",
"role": "user"
},
{
"content": "Thought: Open the Best Buy app from the home screen to access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 924]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_0.png"
] | 10,174
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Open the Best Buy app from the home screen to access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 924]}<image>",
"role": "user"
},
{
"content": "Thought: Click the THREE DOTS to access more options for managing cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [462, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_0.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_1.png"
] | 10,175
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Open the Best Buy app from the home screen to access the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 924]}<image>Thought: Click the THREE DOTS to access more options for managing cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [462, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more items in the cart and locate options to clear them.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_0.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_1.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_2.png"
] | 10,176
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click the THREE DOTS to access more options for managing cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [462, 67]}<image>Thought: Scroll down to view more items in the cart and locate options to clear them.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the option to clear items from the cart on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_1.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_2.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_3.png"
] | 10,177
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Scroll down to view more items in the cart and locate options to clear them.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the option to clear items from the cart on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Search bar to input \"razer blade.\" This step is necessary to find the desired item on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 496]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_2.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_3.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_4.png"
] | 10,178
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Scroll down to find the option to clear items from the cart on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the Search bar to input \"razer blade.\" This step is necessary to find the desired item on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 496]}<image>",
"role": "user"
},
{
"content": "Thought: Click Remove to delete the item currently in the cart before adding a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 1018]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_3.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_4.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_5.png"
] | 10,179
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click on the Search bar to input \"razer blade.\" This step is necessary to find the desired item on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 496]}<image>Thought: Click Remove to delete the item currently in the cart before adding a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 1018]}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to begin looking for the Razer Blade on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [249, 177]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_4.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_5.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_6.png"
] | 10,180
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click Remove to delete the item currently in the cart before adding a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 1018]}<image>Thought: Click Search to begin looking for the Razer Blade on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [249, 177]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_5.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_6.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_7.png"
] | 10,181
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click Search to begin looking for the Razer Blade on Best Buy's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [249, 177]}<image>Thought: Type \"razer blade\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"razer blade\" to select and view available options for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 198]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_6.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_7.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_8.png"
] | 10,182
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Type \"razer blade\" in the search bar to find the desired product.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>Thought: Click on \"razer blade\" to select and view available options for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 198]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the Razer Blade product listed below on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_7.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_8.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_9.png"
] | 10,183
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click on \"razer blade\" to select and view available options for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 198]}<image>Thought: Scroll down to view the Razer Blade product listed below on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Save button to save the Razer Blade for future reference instead of adding it directly to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 745]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_8.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_9.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_10.png"
] | 10,184
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Scroll down to view the Razer Blade product listed below on Best Buy.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the Save button to save the Razer Blade for future reference instead of adding it directly to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 745]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the Razer Blade laptop in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [425, 752]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_9.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_10.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_11.png"
] | 10,185
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear all items from cart on bestbuy. Add razer blade to the cart on bestbuy<image>Thought: Click on the Save button to save the Razer Blade for future reference instead of adding it directly to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 745]}<image>Thought: Click \"Add to Cart\" to include the Razer Blade laptop in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [425, 752]}<image>",
"role": "user"
},
{
"content": "Thought: You completed clearing the cart on BestBuy, so you can proceed with your shopping seamlessly.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7503229340990474002_10.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_11.png",
"training_data/AITW/aitw_images/webshopping/7503229340990474002_12.png"
] | 10,186
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the CHAT icon to seek assistance with adding Alienware Area 51 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 488]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_0.png"
] | 10,187
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click on the CHAT icon to seek assistance with adding Alienware Area 51 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 488]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on the link to view the item details on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 41]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_0.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_1.png"
] | 10,188
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click on the CHAT icon to seek assistance with adding Alienware Area 51 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 488]}<image>Thought: You clicked on the link to view the item details on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 41]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website and proceed with the task.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_0.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_1.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_2.png"
] | 10,189
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: You clicked on the link to view the item details on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 41]}<image>Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website and proceed with the task.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on walmart.com to navigate to the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 86]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_1.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_2.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_3.png"
] | 10,190
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Type \"walmart.com\" in the search bar to navigate to Walmart's website and proceed with the task.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click on walmart.com to navigate to the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 86]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search everything\" bar to begin searching for the Alienware Area 51.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [119, 84]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_2.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_3.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_4.png"
] | 10,191
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click on walmart.com to navigate to the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 86]}<image>Thought: Click the \"Search everything\" bar to begin searching for the Alienware Area 51.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [119, 84]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"alienware area 51\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware area 51\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_3.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_4.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_5.png"
] | 10,192
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click the \"Search everything\" bar to begin searching for the Alienware Area 51.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [119, 84]}<image>Thought: Type \"alienware area 51\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware area 51\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"alienware area 51\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 125]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_4.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_5.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_6.png"
] | 10,193
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Type \"alienware area 51\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware area 51\", \"position\": null}<image>Thought: Click on \"alienware area 51\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 125]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results for \"alienware area 51\" and find the product to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_5.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_6.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_7.png"
] | 10,194
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click on \"alienware area 51\" to select the desired product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 125]}<image>Thought: Scroll down to view more results for \"alienware area 51\" and find the product to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to “alienware area 51” on Walmart’s search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_6.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_7.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_8.png"
] | 10,195
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Scroll down to view more results for \"alienware area 51\" and find the product to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products related to “alienware area 51” on Walmart’s search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"X\" to close any pop-up or overlay that might be blocking options for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 431]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_7.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_8.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_9.png"
] | 10,196
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Scroll down to view more products related to “alienware area 51” on Walmart’s search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"X\" to close any pop-up or overlay that might be blocking options for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 431]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options for the Alienware Area 51.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_8.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_9.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_10.png"
] | 10,197
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Click the \"X\" to close any pop-up or overlay that might be blocking options for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 431]}<image>Thought: Scroll down to view more options for the Alienware Area 51.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Alienware Area 51 product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_9.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_10.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_11.png"
] | 10,198
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 alienware area 51 to the cart on walmart.com<image>Thought: Scroll down to view more options for the Alienware Area 51.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the Alienware Area 51 product in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add\" button to include the Alienware Area 51 in your shopping cart on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [190, 469]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13100245080542780070_10.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_11.png",
"training_data/AITW/aitw_images/webshopping/13100245080542780070_12.png"
] | 10,199
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.