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: Search for \"apple airpods\" on target, select the first entry, and add it to the cart.<image>Thought: Click \"Add to cart\" to select the first entry for Apple AirPods as it's the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [299, 542]}<image>Thought: You would click \"Add to cart\" to finalize adding the Apple AirPods after selecting them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 539]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully navigated the app to find \"apple airpods\" and selected the first entry, indicating your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/4854234231554343604_8.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_9.png",
"training_data/AITW/aitw_images/webshopping/4854234231554343604_10.png"
] | 9,200
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"DOg\" icon to open the browser for target.com. This action is necessary to access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1172]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_0.png"
] | 9,201
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click on the \"DOg\" icon to open the browser for target.com. This action is necessary to access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1172]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: You cannot add \"macbook\" to the cart since you are on negg.com, not target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 95]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_0.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_1.png"
] | 9,202
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click on the \"DOg\" icon to open the browser for target.com. This action is necessary to access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1172]}<image>Thought: Status task impossible: You cannot add \"macbook\" to the cart since you are on negg.com, not target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 95]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target.com\" in the search or type web address bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_0.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_1.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_2.png"
] | 9,203
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Status task impossible: You cannot add \"macbook\" to the cart since you are on negg.com, not target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 95]}<image>Thought: Type \"target.com\" in the search or type web address bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the link for target.com to access the website and view your options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 232]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_1.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_2.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_3.png"
] | 9,204
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Type \"target.com\" in the search or type web address bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"target.com\", \"position\": null}<image>Thought: Click the link for target.com to access the website and view your options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 232]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access the current items I've selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 293]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_2.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_3.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_4.png"
] | 9,205
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click the link for target.com to access the website and view your options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 232]}<image>Thought: Click the SHOPPING CART to access the current items I've selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 293]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to initiate a search for \"macbook\" on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 397]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_3.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_4.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_5.png"
] | 9,206
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click the SHOPPING CART to access the current items I've selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 293]}<image>Thought: Click the Search bar to initiate a search for \"macbook\" on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 397]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_4.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_5.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_6.png"
] | 9,207
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click the Search bar to initiate a search for \"macbook\" on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 397]}<image>Thought: Type \"macbook\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"macbook\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [558, 212]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_5.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_6.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_7.png"
] | 9,208
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Type \"macbook\" in the search bar to find the product on target.com.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"macbook\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [558, 212]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more results for \"macbook\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_6.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_7.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_8.png"
] | 9,209
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click the magnifying glass to initiate a search for \"macbook\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [558, 212]}<image>Thought: Scroll down to see more results for \"macbook\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to \"macbook\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_7.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_8.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_9.png"
] | 9,210
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Scroll down to see more results for \"macbook\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products related to \"macbook\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to \"macbook\" and find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_8.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_9.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_10.png"
] | 9,211
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Scroll down to view more products related to \"macbook\" in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products related to \"macbook\" and find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view more items related to \"macbook\" that may be available for purchase.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_9.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_10.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_11.png"
] | 9,212
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Scroll down to view more products related to \"macbook\" and find the desired item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view more items related to \"macbook\" that may be available for purchase.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Power Adapter as it is a relevant accessory for the \"macbook\" search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 456]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_10.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_11.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_12.png"
] | 9,213
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Scroll up to view more items related to \"macbook\" that may be available for purchase.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on the Power Adapter as it is a relevant accessory for the \"macbook\" search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 456]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the shopping cart button in the GUI to view the cart contents.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_11.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_12.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_13.png"
] | 9,214
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Click on the Power Adapter as it is a relevant accessory for the \"macbook\" search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 456]}<image>Thought: Scroll down to find the shopping cart button in the GUI to view the cart contents.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the selected item in your shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [441, 1138]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_12.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_13.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_14.png"
] | 9,215
|
[
{
"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: View the shopping cart on target.com. Add \"macbook\" to the cart on target.com<image>Thought: Scroll down to find the shopping cart button in the GUI to view the cart contents.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the selected item in your shopping cart on target.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [441, 1138]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the item \"macbook\" has been successfully added to the shopping cart on target.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7256188642867415912_13.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_14.png",
"training_data/AITW/aitw_images/webshopping/7256188642867415912_15.png"
] | 9,216
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the MIC to use voice input for searching \"macbook pro\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 520]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_0.png"
] | 9,217
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click the MIC to use voice input for searching \"macbook pro\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 520]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked \"TAKE PHOTO\" likely to upload a photo for account verification or an identification process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 29]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_0.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_1.png"
] | 9,218
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click the MIC to use voice input for searching \"macbook pro\" on Costco.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 520]}<image>Thought: You clicked \"TAKE PHOTO\" likely to upload a photo for account verification or an identification process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 29]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button on the shopping cart to increase the quantity of \"macbook pro\" before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [15, 27]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_0.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_1.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_2.png"
] | 9,219
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: You clicked \"TAKE PHOTO\" likely to upload a photo for account verification or an identification process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 29]}<image>Thought: Click the PLUS button on the shopping cart to increase the quantity of \"macbook pro\" before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [15, 27]}<image>",
"role": "user"
},
{
"content": "Thought: Click Google to access the search engine for finding \"costco.com\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 138]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_1.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_2.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_3.png"
] | 9,220
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click the PLUS button on the shopping cart to increase the quantity of \"macbook pro\" before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [15, 27]}<image>Thought: Click Google to access the search engine for finding \"costco.com\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 138]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"costco\" in the search bar to find the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_2.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_3.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_4.png"
] | 9,221
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click Google to access the search engine for finding \"costco.com\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [128, 138]}<image>Thought: Type \"costco\" in the search bar to find the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"costco.com\" to navigate to the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 93]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_3.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_4.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_5.png"
] | 9,222
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Type \"costco\" in the search bar to find the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \"costco\", \"position\": null}<image>Thought: Click on \"costco.com\" to navigate to the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 93]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco link to access the website where you can add items to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 285]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_4.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_5.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_6.png"
] | 9,223
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click on \"costco.com\" to navigate to the Costco website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [75, 93]}<image>Thought: Click on the Costco link to access the website where you can add items to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 285]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro\" in the search bar to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_5.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_6.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_7.png"
] | 9,224
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click on the Costco link to access the website where you can add items to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 285]}<image>Thought: Type \"macbook pro\" in the search bar to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to search for \"macbook pro\" on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 293]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_6.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_7.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_8.png"
] | 9,225
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Type \"macbook pro\" in the search bar to find the desired product on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}<image>Thought: Click the MAGNIFYING GLASS to search for \"macbook pro\" on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 293]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Select Options\" to view the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 379]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_7.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_8.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_9.png"
] | 9,226
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click the MAGNIFYING GLASS to search for \"macbook pro\" on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 293]}<image>Thought: Click on \"Select Options\" to view the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 379]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the \"Add to Cart\" button for the MacBook Pro on Costco.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_8.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_9.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_10.png"
] | 9,227
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click on \"Select Options\" to view the product details and add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [214, 379]}<image>Thought: Scroll down to view the \"Add to Cart\" button for the MacBook Pro on Costco.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Cart icon to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 469]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_9.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_10.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_11.png"
] | 9,228
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Scroll down to view the \"Add to Cart\" button for the MacBook Pro on Costco.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Cart icon to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 469]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"View Cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_10.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_11.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_12.png"
] | 9,229
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click the Cart icon to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 469]}<image>Thought: Click on \"View Cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 199]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Checkout button to proceed with the purchase after adding \"macbook pro\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 574]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_11.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_12.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_13.png"
] | 9,230
|
[
{
"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: Add \"macbook pro\" to the cart on costco.com, then select checkout.<image>Thought: Click on \"View Cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 199]}<image>Thought: Click the Checkout button to proceed with the purchase after adding \"macbook pro\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [138, 574]}<image>",
"role": "user"
},
{
"content": "Thought: Check if the macbook pro was successfully added to the cart and proceed to checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9836042322613681332_12.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_13.png",
"training_data/AITW/aitw_images/webshopping/9836042322613681332_14.png"
] | 9,231
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access the app for searching Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_0.png"
] | 9,232
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>Thought: Press home to return to the main screen and access the app for searching Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY because it likely leads to an app or the interface needed to search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 508]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_0.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_1.png"
] | 9,233
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>Thought: Press home to return to the main screen and access the app for searching Walmart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click PLAY because it likely leads to an app or the interface needed to search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 508]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input the desired query for locating the new Nintendo Switch on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 26]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_0.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_1.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_2.png"
] | 9,234
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>Thought: Click PLAY because it likely leads to an app or the interface needed to search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 508]}<image>Thought: Click the search bar to input the desired query for locating the new Nintendo Switch on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 26]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"nintendo switch on walmart\" in the search bar to initiate a web search for the item.\nAction: {\"action\": \"TYPE\", \"value\": \"nintendo switch on walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_1.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_2.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_3.png"
] | 9,235
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>Thought: Click the search bar to input the desired query for locating the new Nintendo Switch on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [109, 26]}<image>Thought: Type \"nintendo switch on walmart\" in the search bar to initiate a web search for the item.\nAction: {\"action\": \"TYPE\", \"value\": \"nintendo switch on walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"nintendo switch on\" to initiate the search for new Nintendo Switch options at Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 58]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_2.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_3.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_4.png"
] | 9,236
|
[
{
"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: Search for the new nintendo switch on Walmart.<image>Thought: Type \"nintendo switch on walmart\" in the search bar to initiate a web search for the item.\nAction: {\"action\": \"TYPE\", \"value\": \"nintendo switch on walmart\", \"position\": null}<image>Thought: Click on \"nintendo switch on\" to initiate the search for new Nintendo Switch options at Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 58]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for the new Nintendo Switch on Walmart through Google.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7783393273376735530_3.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_4.png",
"training_data/AITW/aitw_images/webshopping/7783393273376735530_5.png"
] | 9,237
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the eBay app icon on the home screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_0.png"
] | 9,238
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to find the eBay app icon on the home screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Chrome to open the browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [173, 214]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_0.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_1.png"
] | 9,239
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to find the eBay app icon on the home screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on Chrome to open the browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [173, 214]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the product link to view details and ensure it's the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 35]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_0.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_1.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_2.png"
] | 9,240
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on Chrome to open the browser for searching eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [173, 214]}<image>Thought: Click on the product link to view details and ensure it's the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 35]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the search bar to access the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_1.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_2.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_3.png"
] | 9,241
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the product link to view details and ensure it's the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 35]}<image>Thought: Type \"ebay\" in the search bar to access the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"eb\" and see relevant results on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_2.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_3.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_4.png"
] | 9,242
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"ebay\" in the search bar to access the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>Thought: Press enter to execute the search for \"eb\" and see relevant results on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for anything\" to enter the search input field for finding items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 98]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_3.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_4.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_5.png"
] | 9,243
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Press enter to execute the search for \"eb\" and see relevant results on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on \"Search for anything\" to enter the search input field for finding items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 98]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close any existing cart items and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 68]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_4.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_5.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_6.png"
] | 9,244
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Search for anything\" to enter the search input field for finding items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [81, 98]}<image>Thought: Click the X to close any existing cart items and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 68]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART to view current items in the cart for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_5.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_6.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_7.png"
] | 9,245
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the X to close any existing cart items and start a new search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 68]}<image>Thought: Click on the SHOPPING CART to view current items in the cart for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 70]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Ramoya\" to view the specific details of the first item in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 282]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_6.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_7.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_8.png"
] | 9,246
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the SHOPPING CART to view current items in the cart for clearing them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [228, 70]}<image>Thought: Click on \"Ramoya\" to view the specific details of the first item in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 282]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"macbook pro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 65]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_7.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_8.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_9.png"
] | 9,247
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Ramoya\" to view the specific details of the first item in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 282]}<image>Thought: Click the magnifying glass to initiate a search for \"macbook pro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 65]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input \"macbook pro\" since it is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 409]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_8.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_9.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_10.png"
] | 9,248
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to initiate a search for \"macbook pro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 65]}<image>Thought: Click the search bar to input \"macbook pro\" since it is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 409]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for finding items on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [160, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_9.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_10.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_11.png"
] | 9,249
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the search bar to input \"macbook pro\" since it is empty.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 409]}<image>Thought: Click the magnifying glass to access the search function for finding items on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [160, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook pro\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_10.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_11.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_12.png"
] | 9,250
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to access the search function for finding items on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [160, 67]}<image>Thought: Type \"macbook pro\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"macbook pro\" on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_11.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_12.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_13.png"
] | 9,251
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"macbook pro\" in the search bar to find the desired item on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook pro\", \"position\": null}<image>Thought: Press enter to initiate the search for \"macbook pro\" on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the item named \"3.40Ghz Retina - Big Sur - 3 Year\" to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 256]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_12.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_13.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_14.png"
] | 9,252
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Press enter to initiate the search for \"macbook pro\" on eBay.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on the item named \"3.40Ghz Retina - Big Sur - 3 Year\" to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 256]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the MacBook Pro listing and its price.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_13.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_14.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_15.png"
] | 9,253
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the item named \"3.40Ghz Retina - Big Sur - 3 Year\" to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 256]}<image>Thought: Scroll down to view more details about the MacBook Pro listing and its price.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to store the selected MacBook Pro for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 436]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_14.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_15.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_16.png"
] | 9,254
|
[
{
"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: Clear all items from cart on ebay. Search for \"macbook pro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the MacBook Pro listing and its price.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to store the selected MacBook Pro for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 436]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully completed the task by adding an item to the cart after searching for it on eBay.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14046379948308482101_15.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_16.png",
"training_data/AITW/aitw_images/webshopping/14046379948308482101_17.png"
] | 9,255
|
[
{
"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: Search for the best selling book on Amazon.<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome icon to open the browser for searching best selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 535]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_0.png"
] | 9,256
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Click the Google Chrome icon to open the browser for searching best selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 535]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input the desired book because results for \"the new steph curry shoes\" are not relevant.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 179]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_0.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_1.png"
] | 9,257
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Click the Google Chrome icon to open the browser for searching best selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 535]}<image>Thought: Click the search bar to input the desired book because results for \"the new steph curry shoes\" are not relevant.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 179]}<image>",
"role": "user"
},
{
"content": "Thought: Clear the search field by clicking the X to start a new search for best selling books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_0.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_1.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_2.png"
] | 9,258
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Click the search bar to input the desired book because results for \"the new steph curry shoes\" are not relevant.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 179]}<image>Thought: Clear the search field by clicking the X to start a new search for best selling books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to enter terms related to best-selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_1.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_2.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_3.png"
] | 9,259
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Clear the search field by clicking the X to start a new search for best selling books.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 184]}<image>Thought: Click the search bar to enter terms related to best-selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 190]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to clear the existing search suggestions in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_2.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_3.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_4.png"
] | 9,260
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Click the search bar to enter terms related to best-selling books on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [45, 190]}<image>Thought: Click the X to clear the existing search suggestions in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to specify the query for the best selling book.\nAction: {\"action\": \"TYPE\", \"value\": \" the best selling book\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_3.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_4.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_5.png"
] | 9,261
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Click the X to clear the existing search suggestions in the search bar.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [310, 184]}<image>Thought: Type in the search bar to specify the query for the best selling book.\nAction: {\"action\": \"TYPE\", \"value\": \" the best selling book\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"best selling books\" to select the most relevant suggestion for my search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 230]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_4.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_5.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_6.png"
] | 9,262
|
[
{
"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: Search for the best selling book on Amazon.<image>Thought: Type in the search bar to specify the query for the best selling book.\nAction: {\"action\": \"TYPE\", \"value\": \" the best selling book\", \"position\": null}<image>Thought: Click on \"best selling books\" to select the most relevant suggestion for my search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 230]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"the best selling books\" on the Amazon search bar and found relevant results, indicating task completion.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/11478900946104683050_5.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_6.png",
"training_data/AITW/aitw_images/webshopping/11478900946104683050_7.png"
] | 9,263
|
[
{
"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: Look up the best rated gaming chair on Target.<image>",
"role": "user"
},
{
"content": "Thought: Click the Google app icon to access the search feature for finding products at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 136]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_0.png"
] | 9,264
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Click the Google app icon to access the search feature for finding products at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 136]}<image>",
"role": "user"
},
{
"content": "Thought: Click CHAT to seek assistance or information regarding the best rated gaming chair on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 489]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_0.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_1.png"
] | 9,265
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Click the Google app icon to access the search feature for finding products at Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 136]}<image>Thought: Click CHAT to seek assistance or information regarding the best rated gaming chair on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 489]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that the user clicked on an unrelated link for Theraflu products instead of searching for gaming chairs. Realize the task isn't being addressed, leading to a need to navigate back or search again.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 31]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_0.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_1.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_2.png"
] | 9,266
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Click CHAT to seek assistance or information regarding the best rated gaming chair on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 489]}<image>Thought: Recognize that the user clicked on an unrelated link for Theraflu products instead of searching for gaming chairs. Realize the task isn't being addressed, leading to a need to navigate back or search again.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 31]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Target\" in the search bar to initiate a query for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"Target.\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_1.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_2.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_3.png"
] | 9,267
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Recognize that the user clicked on an unrelated link for Theraflu products instead of searching for gaming chairs. Realize the task isn't being addressed, leading to a need to navigate back or search again.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [166, 31]}<image>Thought: Type \"Target\" in the search bar to initiate a query for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"Target.\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to confirm the search term \"Target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_2.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_3.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_4.png"
] | 9,268
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Type \"Target\" in the search bar to initiate a query for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"Target.\", \"position\": null}<image>Thought: Press enter to confirm the search term \"Target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Target.com - Target Online - Official\" to access the official Target website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 277]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_3.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_4.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_5.png"
] | 9,269
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Press enter to confirm the search term \"Target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on \"Target.com - Target Online - Official\" to access the official Target website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 277]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for finding products on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 155]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_4.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_5.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_6.png"
] | 9,270
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Click on \"Target.com - Target Online - Official\" to access the official Target website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [96, 277]}<image>Thought: Click the magnifying glass to access the search function for finding products on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 155]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"gaming chairs\" option to access the category of interest for best-rated products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 148]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_5.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_6.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_7.png"
] | 9,271
|
[
{
"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: Look up the best rated gaming chair on Target.<image>Thought: Click the magnifying glass to access the search function for finding products on Target.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 155]}<image>Thought: Click on the \"gaming chairs\" option to access the category of interest for best-rated products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 148]}<image>",
"role": "user"
},
{
"content": "Thought: You accessed the Target website and searched for \"gaming chairs\" to find the best rated options. You received results showing various gaming chairs, including their ratings and prices. You reviewed the information presented in order to determine which chair is the best rated. After analyzing these details, you concluded that you successfully found a suitable gaming chair, marking your task as complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8496900341970129330_6.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_7.png",
"training_data/AITW/aitw_images/webshopping/8496900341970129330_8.png"
] | 9,272
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome icon to start browsing for kitchen reno kits on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_0.png"
] | 9,273
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click the Google Chrome icon to start browsing for kitchen reno kits on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to start navigating through the browser options for searching on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_0.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_1.png"
] | 9,274
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click the Google Chrome icon to start browsing for kitchen reno kits on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>Thought: Click PLAY to start navigating through the browser options for searching on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the browser and initiate the search for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_0.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_1.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_2.png"
] | 9,275
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click PLAY to start navigating through the browser options for searching on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>Thought: Click PLAY to open the browser and initiate the search for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_1.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_2.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_3.png"
] | 9,276
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click PLAY to open the browser and initiate the search for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that the search query needs to be modified to find kitchen reno kits. Type \"best rated kitchen reno kits\" in the search bar. Press enter to execute the modified search and see relevant results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [368, 71]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_2.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_3.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_4.png"
] | 9,277
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click on the Chrome icon to open the browser for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 938]}<image>Thought: Recognize that the search query needs to be modified to find kitchen reno kits. Type \"best rated kitchen reno kits\" in the search bar. Press enter to execute the modified search and see relevant results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [368, 71]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Lowes.com\" in the search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Lowes.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_3.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_4.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_5.png"
] | 9,278
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Recognize that the search query needs to be modified to find kitchen reno kits. Type \"best rated kitchen reno kits\" in the search bar. Press enter to execute the modified search and see relevant results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [368, 71]}<image>Thought: Type \"Lowes.com\" in the search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Lowes.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Lowe's Home Improvement to access the website for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 136]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_4.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_5.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_6.png"
] | 9,279
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Type \"Lowes.com\" in the search bar to access the website directly.\nAction: {\"action\": \"TYPE\", \"value\": \"Lowes.com\", \"position\": null}<image>Thought: Click on Lowe's Home Improvement to access the website for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 136]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Lowe's logo to navigate to the home page and initiate a search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 236]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_5.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_6.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_7.png"
] | 9,280
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click on Lowe's Home Improvement to access the website for kitchen reno kits.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [281, 136]}<image>Thought: Click on the Lowe's logo to navigate to the home page and initiate a search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 236]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find kitchen reno kits on Lowes.com.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated kitchen reno kits\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_6.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_7.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_8.png"
] | 9,281
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Click on the Lowe's logo to navigate to the home page and initiate a search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [264, 236]}<image>Thought: Type in the search bar to find kitchen reno kits on Lowes.com.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated kitchen reno kits\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass icon to initiate the search for kitchen renovation kits on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 143]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_7.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_8.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_9.png"
] | 9,282
|
[
{
"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: Search for the best rated kitchen reno kits on Lowes.com<image>Thought: Type in the search bar to find kitchen reno kits on Lowes.com.\nAction: {\"action\": \"TYPE\", \"value\": \"best rated kitchen reno kits\", \"position\": null}<image>Thought: Click the magnifying glass icon to initiate the search for kitchen renovation kits on Lowes.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 143]}<image>",
"role": "user"
},
{
"content": "Thought: The user completed the task by successfully searching for \"best rated kitchen reno kits\" on Lowes.com, as indicated by the displayed results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/3113671926833029264_8.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_9.png",
"training_data/AITW/aitw_images/webshopping/3113671926833029264_10.png"
] | 9,283
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_0.png"
] | 9,284
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the browser icon to access the internet and visit Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 928]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_0.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_1.png"
] | 9,285
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the browser icon to access the internet and visit Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 928]}<image>",
"role": "user"
},
{
"content": "Thought: Click the three dots to access menu options for managing your cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [455, 57]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_0.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_1.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_2.png"
] | 9,286
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click the browser icon to access the internet and visit Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 928]}<image>Thought: Click the three dots to access menu options for managing your cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [455, 57]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view the shopping cart and see if the JBL Charge 4 is already added.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_1.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_2.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_3.png"
] | 9,287
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click the three dots to access menu options for managing your cart on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [455, 57]}<image>Thought: Scroll up to view the shopping cart and see if the JBL Charge 4 is already added.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button to add the JBL Charge 4 to your shopping cart. The GUI shows the current state of your cart, indicating that the operation is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [26, 56]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_2.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_3.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_4.png"
] | 9,288
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Scroll up to view the shopping cart and see if the JBL Charge 4 is already added.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click the PLUS button to add the JBL Charge 4 to your shopping cart. The GUI shows the current state of your cart, indicating that the operation is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [26, 56]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Google to access the search engine for finding Walmart's shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [330, 295]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_3.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_4.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_5.png"
] | 9,289
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click the PLUS button to add the JBL Charge 4 to your shopping cart. The GUI shows the current state of your cart, indicating that the operation is successful.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [26, 56]}<image>Thought: Click on Google to access the search engine for finding Walmart's shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [330, 295]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" in the search bar to access Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"wal;m,aer\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_4.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_5.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_6.png"
] | 9,290
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click on Google to access the search engine for finding Walmart's shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [330, 295]}<image>Thought: Type \"walmart\" in the search bar to access Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"wal;m,aer\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the X to clear the current search input.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 62]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_5.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_6.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_7.png"
] | 9,291
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Type \"walmart\" in the search bar to access Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"wal;m,aer\", \"position\": null}<image>Thought: Click on the X to clear the current search input.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 62]}<image>",
"role": "user"
},
{
"content": "Thought: Click walmart to access the Walmart website and view available products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_6.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_7.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_8.png"
] | 9,292
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click on the X to clear the current search input.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 62]}<image>Thought: Click walmart to access the Walmart website and view available products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 199]}<image>",
"role": "user"
},
{
"content": "Thought: Click Walmart to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 1016]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_7.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_8.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_9.png"
] | 9,293
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click walmart to access the Walmart website and view available products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [114, 199]}<image>Thought: Click Walmart to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 1016]}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'X' to close any pop-up or distraction on the Walmart webpage and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 909]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_8.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_9.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_10.png"
] | 9,294
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click Walmart to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 1016]}<image>Thought: Click the 'X' to close any pop-up or distraction on the Walmart webpage and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 909]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to input the product name \"JBL Charge 4\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [308, 145]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_9.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_10.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_11.png"
] | 9,295
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click the 'X' to close any pop-up or distraction on the Walmart webpage and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 909]}<image>Thought: Click on the search bar to input the product name \"JBL Charge 4\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [308, 145]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"jbl charge 4\" into the search bar to look for the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_10.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_11.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_12.png"
] | 9,296
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click on the search bar to input the product name \"JBL Charge 4\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [308, 145]}<image>Thought: Type \"jbl charge 4\" into the search bar to look for the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"jbl charge 4\" to view product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 380]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_11.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_12.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_13.png"
] | 9,297
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Type \"jbl charge 4\" into the search bar to look for the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}<image>Thought: Click on \"jbl charge 4\" to view product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 380]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add\" button to include the JBL Charge 4 in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [413, 848]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_12.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_13.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_14.png"
] | 9,298
|
[
{
"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: Show the shopping cart on walmart. Add jbl charge 4 to the cart on walmart<image>Thought: Click on \"jbl charge 4\" to view product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [100, 380]}<image>Thought: Click the \"Add\" button to include the JBL Charge 4 in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [413, 848]}<image>",
"role": "user"
},
{
"content": "Thought: View the shopping cart icon to confirm the item has been added successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/8110982500121273031_13.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_14.png",
"training_data/AITW/aitw_images/webshopping/8110982500121273031_15.png"
] | 9,299
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.