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: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Type \"dell alienware\" into the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dell alienware\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"dell alienware\" on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [267, 202]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional options related to shopping on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_10.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_11.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_12.png"
] | 6,200
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Click the magnifying glass to initiate a search for \"dell alienware\" on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [267, 202]}<image>Thought: Scroll down to view additional options related to shopping on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Dell Precision 5530 Laptop to view its details and add it to my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 581]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_11.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_12.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_13.png"
] | 6,201
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Scroll down to view additional options related to shopping on target.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the Dell Precision 5530 Laptop to view its details and add it to my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 581]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products, including the Dell Alienware laptop available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_12.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_13.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_14.png"
] | 6,202
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Click on the Dell Precision 5530 Laptop to view its details and add it to my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 581]}<image>Thought: Scroll down to view more products, including the Dell Alienware laptop available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the search bar for adding Dell Alienware to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_13.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_14.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_15.png"
] | 6,203
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Scroll down to view more products, including the Dell Alienware laptop available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the search bar for adding Dell Alienware to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the price tag to confirm the Dell Alienware is available for online purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 514]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_14.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_15.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_16.png"
] | 6,204
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Scroll down to find the search bar for adding Dell Alienware to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the price tag to confirm the Dell Alienware is available for online purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 514]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the Dell Alienware laptop in the shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 110]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_15.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_16.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_17.png"
] | 6,205
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com. Add dell alienware to the cart on target.com<image>Thought: Click the price tag to confirm the Dell Alienware is available for online purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [193, 514]}<image>Thought: Click \"Add to cart\" to include the Dell Alienware laptop in the shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 110]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully added the Dell Alienware to your cart by clicking the 'Add to cart' button.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14252245433548620745_16.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_17.png",
"training_data/AITW/aitw_images/webshopping/14252245433548620745_18.png"
] | 6,206
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the main screen for Walmart shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_0.png"
] | 6,207
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Press home to exit the current app and return to the main screen for Walmart shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options on the Walmart app for shopping cart management.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_0.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_1.png"
] | 6,208
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Press home to exit the current app and return to the main screen for Walmart shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options on the Walmart app for shopping cart management.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Walmart app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [51, 394]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_0.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_1.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_2.png"
] | 6,209
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Scroll down to view more options on the Walmart app for shopping cart management.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the Walmart app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [51, 394]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Shopping tab to access shopping options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 43]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_1.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_2.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_3.png"
] | 6,210
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click on the Walmart app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [51, 394]}<image>Thought: Click the Shopping tab to access shopping options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 43]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to dismiss the current search entry for \"costco\" and return to a clean state.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 44]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_2.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_3.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_4.png"
] | 6,211
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the Shopping tab to access shopping options on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 43]}<image>Thought: Click the X to dismiss the current search entry for \"costco\" and return to a clean state.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 44]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Walmart to access the website and manage the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 87]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_3.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_4.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_5.png"
] | 6,212
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the X to dismiss the current search entry for \"costco\" and return to a clean state.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 44]}<image>Thought: Click on Walmart to access the website and manage the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 87]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Walmart\" link to visit the official Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 320]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_4.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_5.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_6.png"
] | 6,213
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click on Walmart to access the website and manage the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [59, 87]}<image>Thought: Click on the \"Walmart\" link to visit the official Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 320]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access the items currently saved for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 77]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_5.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_6.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_7.png"
] | 6,214
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click on the \"Walmart\" link to visit the official Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 320]}<image>Thought: Click SHOPPING CART to access the items currently saved for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 77]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view and access the items in the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_6.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_7.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_8.png"
] | 6,215
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click SHOPPING CART to access the items currently saved for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 77]}<image>Thought: Scroll down to view and access the items in the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Remove\" button to delete items from the shopping cart in Walmart's GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [40, 362]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_7.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_8.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_9.png"
] | 6,216
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Scroll down to view and access the items in the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Remove\" button to delete items from the shopping cart in Walmart's GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [40, 362]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Search Walmart\" bar to initiate a search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 38]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_8.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_9.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_10.png"
] | 6,217
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the \"Remove\" button to delete items from the shopping cart in Walmart's GUI.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [40, 362]}<image>Thought: Click on the \"Search Walmart\" bar to initiate a search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 38]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"apple airpods\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_9.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_10.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_11.png"
] | 6,218
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click on the \"Search Walmart\" bar to initiate a search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 38]}<image>Thought: Type \"apple airpods\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"apple airpods\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 84]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_10.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_11.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_12.png"
] | 6,219
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Type \"apple airpods\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"apple airpods\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"apple airpods\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 84]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"+ Add\" button to add \"Apple AirPods\" to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 521]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_11.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_12.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_13.png"
] | 6,220
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the magnifying glass to initiate a search for \"apple airpods\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 84]}<image>Thought: Click the \"+ Add\" button to add \"Apple AirPods\" to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 521]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access the cart and review items for emptying.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [241, 79]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_12.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_13.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_14.png"
] | 6,221
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the \"+ Add\" button to add \"Apple AirPods\" to the shopping cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 521]}<image>Thought: Click the SHOPPING CART to access the cart and review items for emptying.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [241, 79]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue to checkout\" to advance to the payment stage after reviewing the cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 543]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_13.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_14.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_15.png"
] | 6,222
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart. Add \"apple airpods\" to the cart on walmart<image>Thought: Click the SHOPPING CART to access the cart and review items for emptying.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [241, 79]}<image>Thought: Click \"Continue to checkout\" to advance to the payment stage after reviewing the cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 543]}<image>",
"role": "user"
},
{
"content": "Thought: Emptied the shopping cart on Walmart to start fresh for new items. Added \"apple airpods\" to the cart for purchase. Task is complete as intended.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14255991697981364174_14.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_15.png",
"training_data/AITW/aitw_images/webshopping/14255991697981364174_16.png"
] | 6,223
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible because the home screen does not relate to newegg.com or shopping cart operations.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_0.png"
] | 6,224
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible because the home screen does not relate to newegg.com or shopping cart operations.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: status task impossible: The user cannot access Newegg.com from the Photos app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_0.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_1.png"
] | 6,225
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible because the home screen does not relate to newegg.com or shopping cart operations.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: status task impossible: The user cannot access Newegg.com from the Photos app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on the Best Buy sign-in page because you need to log in to your account to empty your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 32]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_0.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_1.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_2.png"
] | 6,226
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: status task impossible: The user cannot access Newegg.com from the Photos app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 473]}<image>Thought: You clicked on the Best Buy sign-in page because you need to log in to your account to empty your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 32]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_1.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_2.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_3.png"
] | 6,227
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: You clicked on the Best Buy sign-in page because you need to log in to your account to empty your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [161, 32]}<image>Thought: Type \"newegg.com\" to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on newegg.com to access the website and start emptying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 104]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_2.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_3.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_4.png"
] | 6,228
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"newegg.com\" to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Click on newegg.com to access the website and start emptying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 104]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Newegg.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 530]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_3.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_4.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_5.png"
] | 6,229
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on newegg.com to access the website and start emptying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 104]}<image>Thought: Click on Newegg.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 530]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 81]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_4.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_5.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_6.png"
] | 6,230
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on Newegg.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 530]}<image>Thought: Click the SHOPPING CART to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 81]}<image>",
"role": "user"
},
{
"content": "Thought: Clicking DELETE removes the item from the shopping cart to complete the task of emptying it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_5.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_6.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_7.png"
] | 6,231
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the SHOPPING CART to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [220, 81]}<image>Thought: Clicking DELETE removes the item from the shopping cart to complete the task of emptying it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 274]}<image>",
"role": "user"
},
{
"content": "Thought: Click on CONTINUE SHOPPING to start searching for products after confirming the cart is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 295]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_6.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_7.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_8.png"
] | 6,232
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Clicking DELETE removes the item from the shopping cart to complete the task of emptying it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 274]}<image>Thought: Click on CONTINUE SHOPPING to start searching for products after confirming the cart is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 295]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar at the top to start a search for \"razer huntsman\" on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 92]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_7.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_8.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_9.png"
] | 6,233
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on CONTINUE SHOPPING to start searching for products after confirming the cart is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [156, 295]}<image>Thought: Click the search bar at the top to start a search for \"razer huntsman\" on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 92]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer huntsman\" in the search bar to find the desired product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_8.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_9.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_10.png"
] | 6,234
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the search bar at the top to start a search for \"razer huntsman\" on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 92]}<image>Thought: Type \"razer huntsman\" in the search bar to find the desired product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Razer Huntsman entry to view its details and options for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 94]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_9.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_10.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_11.png"
] | 6,235
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"razer huntsman\" in the search bar to find the desired product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>Thought: Click on the Razer Huntsman entry to view its details and options for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 94]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Huntsman V2 Analog\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 432]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_10.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_11.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_12.png"
] | 6,236
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Razer Huntsman entry to view its details and options for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 94]}<image>Thought: Click on the \"Huntsman V2 Analog\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 432]}<image>",
"role": "user"
},
{
"content": "Thought: Click ADD TO CART to add the Razer Huntsman keyboard to my shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [115, 553]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_11.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_12.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_13.png"
] | 6,237
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the \"Huntsman V2 Analog\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 432]}<image>Thought: Click ADD TO CART to add the Razer Huntsman keyboard to my shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [115, 553]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access and manage the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [11, 543]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_12.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_13.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_14.png"
] | 6,238
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click ADD TO CART to add the Razer Huntsman keyboard to my shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [115, 553]}<image>Thought: Click the SHOPPING CART to access and manage the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [11, 543]}<image>",
"role": "user"
},
{
"content": "Thought: Click SECURE CHECKOUT to proceed with the payment process for the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 521]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_13.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_14.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_15.png"
] | 6,239
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Search for razer huntsman on newegg.com, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the SHOPPING CART to access and manage the items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [11, 543]}<image>Thought: Click SECURE CHECKOUT to proceed with the payment process for the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 521]}<image>",
"role": "user"
},
{
"content": "Thought: Status task complete indicates the user has successfully emptied the shopping cart on newegg.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3532135897120552171_14.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_15.png",
"training_data/AITW/aitw_images/webshopping/3532135897120552171_16.png"
] | 6,240
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access notifications or messages related to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [488, 1153]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_0.png"
] | 6,241
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Click the ENVELOPE icon to access notifications or messages related to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [488, 1153]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked the link to access the shopping cart page on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 86]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_0.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_1.png"
] | 6,242
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Click the ENVELOPE icon to access notifications or messages related to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [488, 1153]}<image>Thought: You clicked the link to access the shopping cart page on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 86]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target.com\" in the search or type web address bar to access the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_0.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_1.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_2.png"
] | 6,243
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: You clicked the link to access the shopping cart page on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 86]}<image>Thought: Type \"target.com\" in the search or type web address bar to access the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to navigate directly to the Target shopping cart page.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_1.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_2.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_3.png"
] | 6,244
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Type \"target.com\" in the search or type web address bar to access the Target website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>Thought: Press enter to navigate directly to the Target shopping cart page.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to view the items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 253]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_2.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_3.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_4.png"
] | 6,245
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Press enter to navigate directly to the Target shopping cart page.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on the SHOPPING CART icon to view the items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 253]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view all items in the shopping cart for removal options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_3.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_4.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_5.png"
] | 6,246
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Click on the SHOPPING CART icon to view the items added.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [665, 253]}<image>Thought: Scroll down to view all items in the shopping cart for removal options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the items in the shopping cart for emptying.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_4.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_5.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_6.png"
] | 6,247
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Scroll down to view all items in the shopping cart for removal options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the items in the shopping cart for emptying.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove an item from the shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 773]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_5.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_6.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_7.png"
] | 6,248
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Scroll down to view the items in the shopping cart for emptying.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the X to remove an item from the shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 773]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X next to the item in the cart to remove it. This action directly interacts with the item you want to eliminate from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [687, 645]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_6.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_7.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_8.png"
] | 6,249
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Click the X to remove an item from the shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [671, 773]}<image>Thought: Click the X next to the item in the cart to remove it. This action directly interacts with the item you want to eliminate from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [687, 645]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X icon to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [687, 645]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_7.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_8.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_9.png"
] | 6,250
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on target.com.<image>Thought: Click the X next to the item in the cart to remove it. This action directly interacts with the item you want to eliminate from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [687, 645]}<image>Thought: Click the X icon to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [687, 645]}<image>",
"role": "user"
},
{
"content": "Thought: You see the message \"Your cart is empty,\" indicating the shopping cart has been successfully cleared.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/10458456819290281760_8.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_9.png",
"training_data/AITW/aitw_images/webshopping/10458456819290281760_10.png"
] | 6,251
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current settings and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_0.png"
] | 6,252
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Press home to exit the current settings and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"M\" to access the Amazon app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 826]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_0.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_1.png"
] | 6,253
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Press home to exit the current settings and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the \"M\" to access the Amazon app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 826]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the location to change delivery settings for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 78]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_0.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_1.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_2.png"
] | 6,254
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click on the \"M\" to access the Amazon app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 826]}<image>Thought: Click on the location to change delivery settings for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 78]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the amazon.com link to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 734]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_1.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_2.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_3.png"
] | 6,255
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click on the location to change delivery settings for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [348, 78]}<image>Thought: Click on the amazon.com link to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 734]}<image>",
"role": "user"
},
{
"content": "Thought: Click the link to access the Amazon official site for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 414]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_2.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_3.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_4.png"
] | 6,256
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click on the amazon.com link to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [154, 734]}<image>Thought: Click the link to access the Amazon official site for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 414]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Amazon Basics\" to explore available products and find the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 208]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_3.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_4.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_5.png"
] | 6,257
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click the link to access the Amazon official site for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 414]}<image>Thought: Click on \"Amazon Basics\" to explore available products and find the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 208]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_4.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_5.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_6.png"
] | 6,258
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click on \"Amazon Basics\" to explore available products and find the MacBook Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [236, 208]}<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro 15 inch\" in the search bar to find the product. Press enter to execute the search and display results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_5.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_6.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_7.png"
] | 6,259
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro 15 inch\", \"position\": null}<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product. Press enter to execute the search and display results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the star on the product to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 680]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_6.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_7.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_8.png"
] | 6,260
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Type \"macbook pro 15 inch\" in the search bar to find the product. Press enter to execute the search and display results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the star on the product to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 680]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find more products related to \"macbook pro 15 inch\" on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_7.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_8.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_9.png"
] | 6,261
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click the star on the product to add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 680]}<image>Thought: Scroll down to find more products related to \"macbook pro 15 inch\" on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options related to the \"macbook pro 15 inch\" on the Amazon page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_8.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_9.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_10.png"
] | 6,262
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Scroll down to find more products related to \"macbook pro 15 inch\" on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options related to the \"macbook pro 15 inch\" on the Amazon page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the shopping cart and checkout options available for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_9.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_10.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_11.png"
] | 6,263
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Scroll down to view more options related to the \"macbook pro 15 inch\" on the Amazon page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the shopping cart and checkout options available for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options or details related to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_10.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_11.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_12.png"
] | 6,264
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Scroll down to view the shopping cart and checkout options available for \"macbook pro 15 inch.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options or details related to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the desired item in your shopping cart for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 805]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_11.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_12.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_13.png"
] | 6,265
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Scroll down to view more options or details related to the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to include the desired item in your shopping cart for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 805]}<image>",
"role": "user"
},
{
"content": "Thought: Click the yellow \"Proceed to checkout\" button to continue with the purchase of the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [308, 408]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_12.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_13.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_14.png"
] | 6,266
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon. Add \"macbook pro 15 inch\" to the cart on amazon, then select checkout.<image>Thought: Click \"Add to Cart\" to include the desired item in your shopping cart for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [332, 805]}<image>Thought: Click the yellow \"Proceed to checkout\" button to continue with the purchase of the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [308, 408]}<image>",
"role": "user"
},
{
"content": "Thought: The task cannot be completed because the user needs to sign in first on the Amazon login screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15080003219485943561_13.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_14.png",
"training_data/AITW/aitw_images/webshopping/15080003219485943561_15.png"
] | 6,267
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to access the applications menu where Walmart can be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 956]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_0.png"
] | 6,268
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click the NAV BAR CIRCLE to access the applications menu where Walmart can be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 956]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" to search for the Walmart app or website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_0.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_1.png"
] | 6,269
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click the NAV BAR CIRCLE to access the applications menu where Walmart can be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 956]}<image>Thought: Type \"walmart\" to search for the Walmart app or website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on walmart.com to access Walmart's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [155, 164]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_0.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_1.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_2.png"
] | 6,270
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"walmart\" to search for the Walmart app or website in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click on walmart.com to access Walmart's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [155, 164]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin entering the product you want to find on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 164]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_1.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_2.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_3.png"
] | 6,271
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click on walmart.com to access Walmart's website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [155, 164]}<image>Thought: Click the search bar to begin entering the product you want to find on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 164]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer naga\" in the search bar to find the product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_2.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_3.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_4.png"
] | 6,272
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click the search bar to begin entering the product you want to find on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [208, 164]}<image>Thought: Type \"razer naga\" in the search bar to find the product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"razer naga\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 315]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_3.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_4.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_5.png"
] | 6,273
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"razer naga\" in the search bar to find the product quickly.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>Thought: Click on the \"razer naga\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 315]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results for \"razer naga\" and find the first entry in the list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_4.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_5.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_6.png"
] | 6,274
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the \"razer naga\" entry to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [89, 315]}<image>Thought: Scroll down to view more results for \"razer naga\" and find the first entry in the list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the MMO Gaming Mouse to view its details and ensure it's the right product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [360, 322]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_5.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_6.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_7.png"
] | 6,275
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more results for \"razer naga\" and find the first entry in the list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the MMO Gaming Mouse to view its details and ensure it's the right product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [360, 322]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Razer Naga entry to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [317, 974]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_6.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_7.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_8.png"
] | 6,276
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the MMO Gaming Mouse to view its details and ensure it's the right product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [360, 322]}<image>Thought: Click on the Razer Naga entry to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [317, 974]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to include the Razer Naga in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [427, 974]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_7.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_8.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_9.png"
] | 6,277
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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. Search for razer naga on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the Razer Naga entry to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [317, 974]}<image>Thought: Click the \"Add to cart\" button to include the Razer Naga in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [427, 974]}<image>",
"role": "user"
},
{
"content": "Thought: User performed the operation to complete the task of adding Razer Naga to the shopping cart on Walmart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12955673374749195628_8.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_9.png",
"training_data/AITW/aitw_images/webshopping/12955673374749195628_10.png"
] | 6,278
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and access the home screen for eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_0.png"
] | 6,279
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Press home to exit the current app and access the home screen for eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Open eBay app by clicking the icon to access the shopping features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 879]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_0.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_1.png"
] | 6,280
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Press home to exit the current app and access the home screen for eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Open eBay app by clicking the icon to access the shopping features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 879]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that I am currently on Best Buy's website instead of eBay. Understand that to complete the task, I need to navigate back to eBay. Use the back button to return to my previous actions so I can access the eBay app or website directly. Press home if necessary to exit this browser and find the eBay application. Once on eBay, locate my cart and look for an option to clear all items from the cart before adding new items like Bose QuietComfort 35 headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 76]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_0.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_1.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_2.png"
] | 6,281
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Open eBay app by clicking the icon to access the shopping features.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [389, 879]}<image>Thought: Recognize that I am currently on Best Buy's website instead of eBay. Understand that to complete the task, I need to navigate back to eBay. Use the back button to return to my previous actions so I can access the eBay app or website directly. Press home if necessary to exit this browser and find the eBay application. Once on eBay, locate my cart and look for an option to clear all items from the cart before adding new items like Bose QuietComfort 35 headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 76]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the search bar to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_1.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_2.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_3.png"
] | 6,282
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Recognize that I am currently on Best Buy's website instead of eBay. Understand that to complete the task, I need to navigate back to eBay. Use the back button to return to my previous actions so I can access the eBay app or website directly. Press home if necessary to exit this browser and find the eBay application. Once on eBay, locate my cart and look for an option to clear all items from the cart before adding new items like Bose QuietComfort 35 headphones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 76]}<image>Thought: Type \"ebay\" in the search bar to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to access the website and proceed with your shopping tasks.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 302]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_2.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_3.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_4.png"
] | 6,283
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Type \"ebay\" in the search bar to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>Thought: Click the eBay link to access the website and proceed with your shopping tasks.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 302]}<image>",
"role": "user"
},
{
"content": "Thought: Click the eBay link to access the homepage for item management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 369]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_3.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_4.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_5.png"
] | 6,284
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the eBay link to access the website and proceed with your shopping tasks.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 302]}<image>Thought: Click the eBay link to access the homepage for item management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 369]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to access items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 133]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_4.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_5.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_6.png"
] | 6,285
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the eBay link to access the homepage for item management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 369]}<image>Thought: Click on the SHOPPING CART icon to access items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 133]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Remove\" button to delete the unwanted item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [476, 602]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_5.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_6.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_7.png"
] | 6,286
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click on the SHOPPING CART icon to access items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 133]}<image>Thought: Click the \"Remove\" button to delete the unwanted item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [476, 602]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to search for Bose QuietComfort 35 on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 129]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_6.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_7.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_8.png"
] | 6,287
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the \"Remove\" button to delete the unwanted item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [476, 602]}<image>Thought: Click the magnifying glass to search for Bose QuietComfort 35 on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 129]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"bose quietcomfort 35\" in the search bar to find the item to add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_7.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_8.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_9.png"
] | 6,288
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the magnifying glass to search for Bose QuietComfort 35 on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 129]}<image>Thought: Type \"bose quietcomfort 35\" in the search bar to find the item to add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the bose quietcomfort 35 to select this specific product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 398]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_8.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_9.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_10.png"
] | 6,289
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Type \"bose quietcomfort 35\" in the search bar to find the item to add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"bose quietcomfort 35\", \"position\": null}<image>Thought: Click on the bose quietcomfort 35 to select this specific product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 398]}<image>",
"role": "user"
},
{
"content": "Thought: Click the STAR icon to save this Bose QuietComfort 35 item for easier access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [101, 603]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_9.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_10.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_11.png"
] | 6,290
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click on the bose quietcomfort 35 to select this specific product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [148, 398]}<image>Thought: Click the STAR icon to save this Bose QuietComfort 35 item for easier access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [101, 603]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones and confirm you're on the correct item page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_10.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_11.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_12.png"
] | 6,291
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the STAR icon to save this Bose QuietComfort 35 item for easier access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [101, 603]}<image>Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones and confirm you're on the correct item page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones before adding them to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_11.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_12.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_13.png"
] | 6,292
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones and confirm you're on the correct item page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones before adding them 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 Bose QuietComfort 35 in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 979]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_12.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_13.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_14.png"
] | 6,293
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Scroll down to view more details about the Bose QuietComfort 35 headphones before adding them to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to include the Bose QuietComfort 35 in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 979]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"View in cart\" to check the current items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [252, 971]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_13.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_14.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_15.png"
] | 6,294
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the \"Add to cart\" button to include the Bose QuietComfort 35 in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [287, 979]}<image>Thought: Click on \"View in cart\" to check the current items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [252, 971]}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR RECT to access the cart and clear items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [406, 978]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_14.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_15.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_16.png"
] | 6,295
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click on \"View in cart\" to check the current items before clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [252, 971]}<image>Thought: Click the NAV BAR RECT to access the cart and clear items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [406, 978]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View cart\" to access the current items in the shopping cart on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [268, 971]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_15.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_16.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_17.png"
] | 6,296
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 ebay. Add bose quietcomfort 35 to the cart on ebay<image>Thought: Click the NAV BAR RECT to access the cart and clear items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [406, 978]}<image>Thought: Click \"View cart\" to access the current items in the shopping cart on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [268, 971]}<image>",
"role": "user"
},
{
"content": "Thought: The task is marked complete after adding the Bose QuietComfort 35 to the cart, indicating success.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4073358395218300551_16.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_17.png",
"training_data/AITW/aitw_images/webshopping/4073358395218300551_18.png"
] | 6,297
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Girl on the Train' on Goodreads.<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app and begin the search for 'The Girl on the Train' on Goodreads.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 484]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9974409779259963340_0.png"
] | 6,298
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 Girl on the Train' on Goodreads.<image>Thought: Click PLAY to open the app and begin the search for 'The Girl on the Train' on Goodreads.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 484]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input text for the desired book title.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [124, 34]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9974409779259963340_0.png",
"training_data/AITW/aitw_images/webshopping/9974409779259963340_1.png"
] | 6,299
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.