messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open a new tab in the chrome app<image>Thought: Click CHAT to access the Chrome app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 472]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the three dots to access the Chrome menu options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 32]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/12693930241255467158_0.png",
"training_data/AITW/aitw_images/general/12693930241255467158_1.png"
] | 2,600
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open a new tab in the chrome app<image>Thought: Click CHAT to access the Chrome app from the home screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 472]}<image>Thought: Click on the three dots to access the Chrome menu options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 32]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button to initiate the process of opening a new tab in the Chrome app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [22, 40]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/12693930241255467158_0.png",
"training_data/AITW/aitw_images/general/12693930241255467158_1.png",
"training_data/AITW/aitw_images/general/12693930241255467158_2.png"
] | 2,601
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Open a new tab in the chrome app<image>Thought: Click on the three dots to access the Chrome menu options.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [222, 32]}<image>Thought: Click the PLUS button to initiate the process of opening a new tab in the Chrome app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [22, 40]}<image>",
"role": "user"
},
{
"content": "Thought: Tap the Chrome app icon to open the browser interface. Ensure you're on the main page to check for tab options. Locate and select the new tab option indicated for task completion. Confirm that a new tab appears, indicating success in opening a new browsing session.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/12693930241255467158_1.png",
"training_data/AITW/aitw_images/general/12693930241255467158_2.png",
"training_data/AITW/aitw_images/general/12693930241255467158_3.png"
] | 2,602
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Maps app and access it for searching sushi restaurants.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_0.png"
] | 2,603
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Scroll down to find the Maps app and access it for searching sushi restaurants.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Maps icon to open the application for searching sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 970]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_0.png",
"training_data/AITW/aitw_images/general/15503007091361700120_1.png"
] | 2,604
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Scroll down to find the Maps app and access it for searching sushi restaurants.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Maps icon to open the application for searching sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 970]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Search here\" to enter the search query for top rated sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 87]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_0.png",
"training_data/AITW/aitw_images/general/15503007091361700120_1.png",
"training_data/AITW/aitw_images/general/15503007091361700120_2.png"
] | 2,605
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Click the Maps icon to open the application for searching sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 970]}<image>Thought: Click \"Search here\" to enter the search query for top rated sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 87]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search here\" bar to begin searching for sushi restaurants on Maps.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [183, 116]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_1.png",
"training_data/AITW/aitw_images/general/15503007091361700120_2.png",
"training_data/AITW/aitw_images/general/15503007091361700120_3.png"
] | 2,606
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Click \"Search here\" to enter the search query for top rated sushi restaurants.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 87]}<image>Thought: Click the \"Search here\" bar to begin searching for sushi restaurants on Maps.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [183, 116]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"top rated sushi restaurants\" in the search bar to find desired sushi places.\nAction: {\"action\": \"TYPE\", \"value\": \"top rated sushi restaurants\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_2.png",
"training_data/AITW/aitw_images/general/15503007091361700120_3.png",
"training_data/AITW/aitw_images/general/15503007091361700120_4.png"
] | 2,607
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Click the \"Search here\" bar to begin searching for sushi restaurants on Maps.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [183, 116]}<image>Thought: Type \"top rated sushi restaurants\" in the search bar to find desired sushi places.\nAction: {\"action\": \"TYPE\", \"value\": \"top rated sushi restaurants\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"top rated sushi restaurants near me\" to select the best option for my location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [483, 196]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_3.png",
"training_data/AITW/aitw_images/general/15503007091361700120_4.png",
"training_data/AITW/aitw_images/general/15503007091361700120_5.png"
] | 2,608
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 top rated sushi restaurants on Maps<image>Thought: Type \"top rated sushi restaurants\" in the search bar to find desired sushi places.\nAction: {\"action\": \"TYPE\", \"value\": \"top rated sushi restaurants\", \"position\": null}<image>Thought: Click on \"top rated sushi restaurants near me\" to select the best option for my location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [483, 196]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully searched for sushi restaurants by entering “top rated sushi restaurants near me” into the search bar.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15503007091361700120_4.png",
"training_data/AITW/aitw_images/general/15503007091361700120_5.png",
"training_data/AITW/aitw_images/general/15503007091361700120_6.png"
] | 2,609
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_0.png"
] | 2,610
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to reveal more options or settings related to the Lyft app on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_0.png",
"training_data/AITW/aitw_images/general/11473029105200619178_1.png"
] | 2,611
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Scroll down to reveal more options or settings related to the Lyft app on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more apps in the app drawer to find the Lyft app settings.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_0.png",
"training_data/AITW/aitw_images/general/11473029105200619178_1.png",
"training_data/AITW/aitw_images/general/11473029105200619178_2.png"
] | 2,612
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Scroll down to reveal more options or settings related to the Lyft app on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more apps in the app drawer to find the Lyft app settings.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Select the PLAY icon to access the game or app where Lyft settings might be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 509]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_1.png",
"training_data/AITW/aitw_images/general/11473029105200619178_2.png",
"training_data/AITW/aitw_images/general/11473029105200619178_3.png"
] | 2,613
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Scroll down to view more apps in the app drawer to find the Lyft app settings.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Select the PLAY icon to access the game or app where Lyft settings might be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 509]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for finding the Lyft app's settings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 69]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_2.png",
"training_data/AITW/aitw_images/general/11473029105200619178_3.png",
"training_data/AITW/aitw_images/general/11473029105200619178_4.png"
] | 2,614
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Select the PLAY icon to access the game or app where Lyft settings might be found.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 509]}<image>Thought: Click the magnifying glass to access the search function for finding the Lyft app's settings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 69]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the search results and access the main screen for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 77]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_3.png",
"training_data/AITW/aitw_images/general/11473029105200619178_4.png",
"training_data/AITW/aitw_images/general/11473029105200619178_5.png"
] | 2,615
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Click the magnifying glass to access the search function for finding the Lyft app's settings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [293, 69]}<image>Thought: Click the X to close the search results and access the main screen for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 77]}<image>",
"role": "user"
},
{
"content": "Thought: You need to find the Lyft app, so type \"Lyft app\" in the search bar. By entering this query, you can quickly locate the settings for that specific app.\nAction: {\"action\": \"TYPE\", \"value\": \"Lyft app\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_4.png",
"training_data/AITW/aitw_images/general/11473029105200619178_5.png",
"training_data/AITW/aitw_images/general/11473029105200619178_6.png"
] | 2,616
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: Click the X to close the search results and access the main screen for further navigation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 77]}<image>Thought: You need to find the Lyft app, so type \"Lyft app\" in the search bar. By entering this query, you can quickly locate the settings for that specific app.\nAction: {\"action\": \"TYPE\", \"value\": \"Lyft app\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for settings related to the Lyft app.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_5.png",
"training_data/AITW/aitw_images/general/11473029105200619178_6.png",
"training_data/AITW/aitw_images/general/11473029105200619178_7.png"
] | 2,617
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Check the settings for the Lyft app<image>Thought: You need to find the Lyft app, so type \"Lyft app\" in the search bar. By entering this query, you can quickly locate the settings for that specific app.\nAction: {\"action\": \"TYPE\", \"value\": \"Lyft app\", \"position\": null}<image>Thought: Press enter to initiate the search for settings related to the Lyft app.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Open the Lyft app to access its settings. Navigate to the settings section to review various options available. Confirm the settings have been checked and ensure they meet my preferences. Indicate that the task is complete since I successfully accessed and reviewed the settings.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11473029105200619178_6.png",
"training_data/AITW/aitw_images/general/11473029105200619178_7.png",
"training_data/AITW/aitw_images/general/11473029105200619178_8.png"
] | 2,618
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to search for the answer about the size of the sun in available apps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_0.png"
] | 2,619
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Scroll down to search for the answer about the size of the sun in available apps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Select the GOOGLE icon to access the internet for information about the sun's size.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 391]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_0.png",
"training_data/AITW/aitw_images/general/16806979190284058471_1.png"
] | 2,620
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Scroll down to search for the answer about the size of the sun in available apps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Select the GOOGLE icon to access the internet for information about the sun's size.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 391]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Books option to find literature related to the size of the sun.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_0.png",
"training_data/AITW/aitw_images/general/16806979190284058471_1.png",
"training_data/AITW/aitw_images/general/16806979190284058471_2.png"
] | 2,621
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Select the GOOGLE icon to access the internet for information about the sun's size.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 391]}<image>Thought: Click on the Books option to find literature related to the size of the sun.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Click the 'X' to clear the current search and prepare for a new query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 37]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_1.png",
"training_data/AITW/aitw_images/general/16806979190284058471_2.png",
"training_data/AITW/aitw_images/general/16806979190284058471_3.png"
] | 2,622
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Click on the Books option to find literature related to the size of the sun.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 67]}<image>Thought: Click the 'X' to clear the current search and prepare for a new query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 37]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"How big is the sun\" into the search bar to seek information about the sun's size.\nAction: {\"action\": \"TYPE\", \"value\": \"How big is the sun\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_2.png",
"training_data/AITW/aitw_images/general/16806979190284058471_3.png",
"training_data/AITW/aitw_images/general/16806979190284058471_4.png"
] | 2,623
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Click the 'X' to clear the current search and prepare for a new query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 37]}<image>Thought: Type \"How big is the sun\" into the search bar to seek information about the sun's size.\nAction: {\"action\": \"TYPE\", \"value\": \"How big is the sun\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"sun\" to retrieve specific information about its size from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 70]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_3.png",
"training_data/AITW/aitw_images/general/16806979190284058471_4.png",
"training_data/AITW/aitw_images/general/16806979190284058471_5.png"
] | 2,624
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How big is the sun?<image>Thought: Type \"How big is the sun\" into the search bar to seek information about the sun's size.\nAction: {\"action\": \"TYPE\", \"value\": \"How big is the sun\", \"position\": null}<image>Thought: Click on \"sun\" to retrieve specific information about its size from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 70]}<image>",
"role": "user"
},
{
"content": "Thought: You entered a query about the size of the sun. The search engine provided relevant information about the sun's size. You checked the result, confirming that your question was answered satisfactorily.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/16806979190284058471_4.png",
"training_data/AITW/aitw_images/general/16806979190284058471_5.png",
"training_data/AITW/aitw_images/general/16806979190284058471_6.png"
] | 2,625
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current settings and return to the main screen for searching flights.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_0.png"
] | 2,626
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Press home to exit the current settings and return to the main screen for searching flights.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Google icon to access the search engine for flight information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 914]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_0.png",
"training_data/AITW/aitw_images/general/11802144814730732238_1.png"
] | 2,627
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Press home to exit the current settings and return to the main screen for searching flights.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Google icon to access the search engine for flight information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 914]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Google to access the search engine for finding flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 914]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_0.png",
"training_data/AITW/aitw_images/general/11802144814730732238_1.png",
"training_data/AITW/aitw_images/general/11802144814730732238_2.png"
] | 2,628
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click the Google icon to access the search engine for flight information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [235, 914]}<image>Thought: Click on Google to access the search engine for finding flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 914]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Best\" to refine flight search results based on popularity or quality for Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 317]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_1.png",
"training_data/AITW/aitw_images/general/11802144814730732238_2.png",
"training_data/AITW/aitw_images/general/11802144814730732238_3.png"
] | 2,629
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click on Google to access the search engine for finding flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 914]}<image>Thought: Click \"Best\" to refine flight search results based on popularity or quality for Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 317]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to clear the previous search for more relevant results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [636, 109]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_2.png",
"training_data/AITW/aitw_images/general/11802144814730732238_3.png",
"training_data/AITW/aitw_images/general/11802144814730732238_4.png"
] | 2,630
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click \"Best\" to refine flight search results based on popularity or quality for Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [414, 317]}<image>Thought: Click the X to clear the previous search for more relevant results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [636, 109]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"fort wayne indiana mayor tom\" to view relevant information about the mayor before proceeding with flight searches.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 76]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_3.png",
"training_data/AITW/aitw_images/general/11802144814730732238_4.png",
"training_data/AITW/aitw_images/general/11802144814730732238_5.png"
] | 2,631
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click the X to clear the previous search for more relevant results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [636, 109]}<image>Thought: Click on \"fort wayne indiana mayor tom\" to view relevant information about the mayor before proceeding with flight searches.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 76]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Search for flights from Tokyo to Seoul\" in the search bar to initiate the flight search process.\nAction: {\"action\": \"TYPE\", \"value\": \"Search for flights from Tokyo to Seoul \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_4.png",
"training_data/AITW/aitw_images/general/11802144814730732238_5.png",
"training_data/AITW/aitw_images/general/11802144814730732238_6.png"
] | 2,632
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click on \"fort wayne indiana mayor tom\" to view relevant information about the mayor before proceeding with flight searches.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [350, 76]}<image>Thought: Type \"Search for flights from Tokyo to Seoul\" in the search bar to initiate the flight search process.\nAction: {\"action\": \"TYPE\", \"value\": \"Search for flights from Tokyo to Seoul \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to initiate the flight search process from Tokyo to Seoul using the search function.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [288, 89]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_5.png",
"training_data/AITW/aitw_images/general/11802144814730732238_6.png",
"training_data/AITW/aitw_images/general/11802144814730732238_7.png"
] | 2,633
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Type \"Search for flights from Tokyo to Seoul\" in the search bar to initiate the flight search process.\nAction: {\"action\": \"TYPE\", \"value\": \"Search for flights from Tokyo to Seoul \", \"position\": null}<image>Thought: Click Search to initiate the flight search process from Tokyo to Seoul using the search function.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [288, 89]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the text input field to start typing the flight search query. Type \"flights from tokyo to seoul south korea\" to specify the travel details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 317]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_6.png",
"training_data/AITW/aitw_images/general/11802144814730732238_7.png",
"training_data/AITW/aitw_images/general/11802144814730732238_8.png"
] | 2,634
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click Search to initiate the flight search process from Tokyo to Seoul using the search function.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [288, 89]}<image>Thought: Click on the text input field to start typing the flight search query. Type \"flights from tokyo to seoul south korea\" to specify the travel details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 317]}<image>",
"role": "user"
},
{
"content": "Thought: Click on 'Class' to explore different flight class options for the search results displayed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 769]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_7.png",
"training_data/AITW/aitw_images/general/11802144814730732238_8.png",
"training_data/AITW/aitw_images/general/11802144814730732238_9.png"
] | 2,635
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click on the text input field to start typing the flight search query. Type \"flights from tokyo to seoul south korea\" to specify the travel details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 317]}<image>Thought: Click on 'Class' to explore different flight class options for the search results displayed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 769]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Accept\" button to permit cookie usage and enhance browsing experience for flight search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [554, 1136]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_8.png",
"training_data/AITW/aitw_images/general/11802144814730732238_9.png",
"training_data/AITW/aitw_images/general/11802144814730732238_10.png"
] | 2,636
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click on 'Class' to explore different flight class options for the search results displayed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 769]}<image>Thought: Click the \"Accept\" button to permit cookie usage and enhance browsing experience for flight search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [554, 1136]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more flight options and details for the search query.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_9.png",
"training_data/AITW/aitw_images/general/11802144814730732238_10.png",
"training_data/AITW/aitw_images/general/11802144814730732238_11.png"
] | 2,637
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Click the \"Accept\" button to permit cookie usage and enhance browsing experience for flight search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [554, 1136]}<image>Thought: Scroll down to view more flight options and details for the search query.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen where flight options might be available for Tokyo to Seoul.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_10.png",
"training_data/AITW/aitw_images/general/11802144814730732238_11.png",
"training_data/AITW/aitw_images/general/11802144814730732238_12.png"
] | 2,638
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Scroll down to view more flight options and details for the search query.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Press back to return to the previous screen where flight options might be available for Tokyo to Seoul.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_11.png",
"training_data/AITW/aitw_images/general/11802144814730732238_12.png",
"training_data/AITW/aitw_images/general/11802144814730732238_13.png"
] | 2,639
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Press back to return to the previous screen where flight options might be available for Tokyo to Seoul.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Flights\" to access the flight search options and confirm the departure and arrival cities. Then, read the search bar to ensure it displays \"search for flights from tokyo to seoul,\" confirming your input is accurate. Click on the highlighted link with \"Tokyo to Seoul Flight\" for more details on available flights.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [339, 759]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_12.png",
"training_data/AITW/aitw_images/general/11802144814730732238_13.png",
"training_data/AITW/aitw_images/general/11802144814730732238_14.png"
] | 2,640
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 flights from Tokyo to Seoul<image>Thought: Scroll down to view more search results related to flights from Tokyo to Seoul.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"Flights\" to access the flight search options and confirm the departure and arrival cities. Then, read the search bar to ensure it displays \"search for flights from tokyo to seoul,\" confirming your input is accurate. Click on the highlighted link with \"Tokyo to Seoul Flight\" for more details on available flights.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [339, 759]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete as the flight options from Tokyo to Seoul are successfully displayed on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/11802144814730732238_13.png",
"training_data/AITW/aitw_images/general/11802144814730732238_14.png",
"training_data/AITW/aitw_images/general/11802144814730732238_15.png"
] | 2,641
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Play Store icon to start the app installation process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 888]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_0.png"
] | 2,642
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the Google Play Store icon to start the app installation process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 888]}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to access the app drawer for searching Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 1107]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_0.png",
"training_data/AITW/aitw_images/general/17197549683182510527_1.png"
] | 2,643
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the Google Play Store icon to start the app installation process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [364, 888]}<image>Thought: Click the NAV BAR CIRCLE to access the app drawer for searching Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 1107]}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to access the app store where I can search for Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 887]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_0.png",
"training_data/AITW/aitw_images/general/17197549683182510527_1.png",
"training_data/AITW/aitw_images/general/17197549683182510527_2.png"
] | 2,644
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the NAV BAR CIRCLE to access the app drawer for searching Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [278, 1107]}<image>Thought: Click PLAY to access the app store where I can search for Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 887]}<image>",
"role": "user"
},
{
"content": "Thought: Click the CALL icon to open the phone app for assistance or communication regarding the Spotify installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [117, 650]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_1.png",
"training_data/AITW/aitw_images/general/17197549683182510527_2.png",
"training_data/AITW/aitw_images/general/17197549683182510527_3.png"
] | 2,645
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click PLAY to access the app store where I can search for Spotify.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [266, 887]}<image>Thought: Click the CALL icon to open the phone app for assistance or communication regarding the Spotify installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [117, 650]}<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app store and search for the Spotify app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 894]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_2.png",
"training_data/AITW/aitw_images/general/17197549683182510527_3.png",
"training_data/AITW/aitw_images/general/17197549683182510527_4.png"
] | 2,646
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the CALL icon to open the phone app for assistance or communication regarding the Spotify installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [117, 650]}<image>Thought: Click PLAY to open the app store and search for the Spotify app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 894]}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to access the search function in the Google Play Store.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 72]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_3.png",
"training_data/AITW/aitw_images/general/17197549683182510527_4.png",
"training_data/AITW/aitw_images/general/17197549683182510527_5.png"
] | 2,647
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click PLAY to open the app store and search for the Spotify app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 894]}<image>Thought: Click the MAGNIFYING GLASS to access the search function in the Google Play Store.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 72]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to clear the current search for better results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_4.png",
"training_data/AITW/aitw_images/general/17197549683182510527_5.png",
"training_data/AITW/aitw_images/general/17197549683182510527_6.png"
] | 2,648
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the MAGNIFYING GLASS to access the search function in the Google Play Store.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [428, 72]}<image>Thought: Click the X to clear the current search for better results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for apps & games\" to begin finding the Spotify app for installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 73]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_5.png",
"training_data/AITW/aitw_images/general/17197549683182510527_6.png",
"training_data/AITW/aitw_images/general/17197549683182510527_7.png"
] | 2,649
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click the X to clear the current search for better results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 73]}<image>Thought: Click on \"Search for apps & games\" to begin finding the Spotify app for installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 73]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"Spotify\" in the search bar to find the app for installation.\nAction: {\"action\": \"TYPE\", \"value\": \"Spotify\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_6.png",
"training_data/AITW/aitw_images/general/17197549683182510527_7.png",
"training_data/AITW/aitw_images/general/17197549683182510527_8.png"
] | 2,650
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Click on \"Search for apps & games\" to begin finding the Spotify app for installation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [304, 73]}<image>Thought: Type \"Spotify\" in the search bar to find the app for installation.\nAction: {\"action\": \"TYPE\", \"value\": \"Spotify\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You click on \"spotify\" in the search results to access the app installation page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [140, 144]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_7.png",
"training_data/AITW/aitw_images/general/17197549683182510527_8.png",
"training_data/AITW/aitw_images/general/17197549683182510527_9.png"
] | 2,651
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: Type \"Spotify\" in the search bar to find the app for installation.\nAction: {\"action\": \"TYPE\", \"value\": \"Spotify\", \"position\": null}<image>Thought: You click on \"spotify\" in the search results to access the app installation page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [140, 144]}<image>",
"role": "user"
},
{
"content": "Thought: Click Install to proceed with the downloading and installation of the Spotify app shown on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [470, 165]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_8.png",
"training_data/AITW/aitw_images/general/17197549683182510527_9.png",
"training_data/AITW/aitw_images/general/17197549683182510527_10.png"
] | 2,652
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Install the Spotify app<image>Thought: You click on \"spotify\" in the search results to access the app installation page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [140, 144]}<image>Thought: Click Install to proceed with the downloading and installation of the Spotify app shown on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [470, 165]}<image>",
"role": "user"
},
{
"content": "Thought: You would perform the operation because the Spotify app is shown as installed, confirming successful installation.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/17197549683182510527_9.png",
"training_data/AITW/aitw_images/general/17197549683182510527_10.png",
"training_data/AITW/aitw_images/general/17197549683182510527_11.png"
] | 2,653
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_0.png"
] | 2,654
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLAY button to open the app that will help find directions to McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [512, 1133]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_0.png",
"training_data/AITW/aitw_images/general/3183826424566980538_1.png"
] | 2,655
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Press home to exit the current app and access the main screen for navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the PLAY button to open the app that will help find directions to McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [512, 1133]}<image>",
"role": "user"
},
{
"content": "Thought: Click the link to access relevant information, hoping it provides directions or a map to the nearest McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [323, 98]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_0.png",
"training_data/AITW/aitw_images/general/3183826424566980538_1.png",
"training_data/AITW/aitw_images/general/3183826424566980538_2.png"
] | 2,656
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Click the PLAY button to open the app that will help find directions to McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [512, 1133]}<image>Thought: Click the link to access relevant information, hoping it provides directions or a map to the nearest McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [323, 98]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to query directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_1.png",
"training_data/AITW/aitw_images/general/3183826424566980538_2.png",
"training_data/AITW/aitw_images/general/3183826424566980538_3.png"
] | 2,657
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Click the link to access relevant information, hoping it provides directions or a map to the nearest McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [323, 98]}<image>Thought: Type in the search bar to query directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You want to find directions to the nearest McDonald's, so you entered your query in the search bar and pressed enter.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_2.png",
"training_data/AITW/aitw_images/general/3183826424566980538_3.png",
"training_data/AITW/aitw_images/general/3183826424566980538_4.png"
] | 2,658
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Type in the search bar to query directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}<image>Thought: You want to find directions to the nearest McDonald's, so you entered your query in the search bar and pressed enter.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type your query in the search bar to find directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_3.png",
"training_data/AITW/aitw_images/general/3183826424566980538_4.png",
"training_data/AITW/aitw_images/general/3183826424566980538_5.png"
] | 2,659
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: You want to find directions to the nearest McDonald's, so you entered your query in the search bar and pressed enter.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Type your query in the search bar to find directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click “Locate your” to access the feature for finding the nearest McDonald's location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [519, 438]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_4.png",
"training_data/AITW/aitw_images/general/3183826424566980538_5.png",
"training_data/AITW/aitw_images/general/3183826424566980538_6.png"
] | 2,660
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Type your query in the search bar to find directions to the nearest McDonald's.\nAction: {\"action\": \"TYPE\", \"value\": \"How do I get to the nearest McDonalds?\", \"position\": null}<image>Thought: Click “Locate your” to access the feature for finding the nearest McDonald's location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [519, 438]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more related searches for finding a nearby McDonald's.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_5.png",
"training_data/AITW/aitw_images/general/3183826424566980538_6.png",
"training_data/AITW/aitw_images/general/3183826424566980538_7.png"
] | 2,661
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Click “Locate your” to access the feature for finding the nearest McDonald's location.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [519, 438]}<image>Thought: Scroll down to view more related searches for finding a nearby McDonald's.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view more options related to finding nearby McDonald's locations.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_6.png",
"training_data/AITW/aitw_images/general/3183826424566980538_7.png",
"training_data/AITW/aitw_images/general/3183826424566980538_8.png"
] | 2,662
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Scroll down to view more related searches for finding a nearby McDonald's.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view more options related to finding nearby McDonald's locations.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to see more options for finding McDonald's nearby.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_7.png",
"training_data/AITW/aitw_images/general/3183826424566980538_8.png",
"training_data/AITW/aitw_images/general/3183826424566980538_9.png"
] | 2,663
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Scroll up to view more options related to finding nearby McDonald's locations.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to see more options for finding McDonald's nearby.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on Maps to access location services for finding nearby McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [104, 181]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_8.png",
"training_data/AITW/aitw_images/general/3183826424566980538_9.png",
"training_data/AITW/aitw_images/general/3183826424566980538_10.png"
] | 2,664
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How do I get to the nearest McDonalds?<image>Thought: Scroll up to see more options for finding McDonald's nearby.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on Maps to access location services for finding nearby McDonald's.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [104, 181]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully found directions to the nearest McDonald's, confirming they have completed their task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/3183826424566980538_9.png",
"training_data/AITW/aitw_images/general/3183826424566980538_10.png",
"training_data/AITW/aitw_images/general/3183826424566980538_11.png"
] | 2,665
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What's the weather like in Mumbai?<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the Settings app and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/10342470313437605382_0.png"
] | 2,666
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What's the weather like in Mumbai?<image>Thought: Press home to exit the Settings app and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR RECT to access the app menu for checking the weather.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 546]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/10342470313437605382_0.png",
"training_data/AITW/aitw_images/general/10342470313437605382_1.png"
] | 2,667
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What's the weather like in Mumbai?<image>Thought: Press home to exit the Settings app and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR RECT to access the app menu for checking the weather.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 546]}<image>",
"role": "user"
},
{
"content": "Thought: Type the question in the search bar to find the weather information for Mumbai.\nAction: {\"action\": \"TYPE\", \"value\": \"What's the weather like in Mumbai?\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/10342470313437605382_0.png",
"training_data/AITW/aitw_images/general/10342470313437605382_1.png",
"training_data/AITW/aitw_images/general/10342470313437605382_2.png"
] | 2,668
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What's the weather like in Mumbai?<image>Thought: Click the NAV BAR RECT to access the app menu for checking the weather.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [157, 546]}<image>Thought: Type the question in the search bar to find the weather information for Mumbai.\nAction: {\"action\": \"TYPE\", \"value\": \"What's the weather like in Mumbai?\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to enter the query about Mumbai's weather.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [177, 62]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/10342470313437605382_1.png",
"training_data/AITW/aitw_images/general/10342470313437605382_2.png",
"training_data/AITW/aitw_images/general/10342470313437605382_3.png"
] | 2,669
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What's the weather like in Mumbai?<image>Thought: Type the question in the search bar to find the weather information for Mumbai.\nAction: {\"action\": \"TYPE\", \"value\": \"What's the weather like in Mumbai?\", \"position\": null}<image>Thought: Click on the search bar to enter the query about Mumbai's weather.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [177, 62]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully queried \"what's the weather like in Mumbai\" in the search bar, displaying the relevant weather information.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/10342470313437605382_2.png",
"training_data/AITW/aitw_images/general/10342470313437605382_3.png",
"training_data/AITW/aitw_images/general/10342470313437605382_4.png"
] | 2,670
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Google the capital of Peru<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google app icon to start searching for information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 841]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13262308062377949284_0.png"
] | 2,671
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Google the capital of Peru<image>Thought: Click on the Google app icon to start searching for information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 841]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to edit the query for capital of Peru.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 60]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13262308062377949284_0.png",
"training_data/AITW/aitw_images/general/13262308062377949284_1.png"
] | 2,672
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Google the capital of Peru<image>Thought: Click on the Google app icon to start searching for information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 841]}<image>Thought: Click on the search bar to edit the query for capital of Peru.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 60]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find information quickly about Peru's capital.\nAction: {\"action\": \"TYPE\", \"value\": \"peru capital\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13262308062377949284_0.png",
"training_data/AITW/aitw_images/general/13262308062377949284_1.png",
"training_data/AITW/aitw_images/general/13262308062377949284_2.png"
] | 2,673
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Google the capital of Peru<image>Thought: Click on the search bar to edit the query for capital of Peru.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 60]}<image>Thought: Type in the search bar to find information quickly about Peru's capital.\nAction: {\"action\": \"TYPE\", \"value\": \"peru capital\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"peru capital\" because it directly matches the search query and likely leads to the desired information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 195]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13262308062377949284_1.png",
"training_data/AITW/aitw_images/general/13262308062377949284_2.png",
"training_data/AITW/aitw_images/general/13262308062377949284_3.png"
] | 2,674
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Google the capital of Peru<image>Thought: Type in the search bar to find information quickly about Peru's capital.\nAction: {\"action\": \"TYPE\", \"value\": \"peru capital\", \"position\": null}<image>Thought: Click on \"peru capital\" because it directly matches the search query and likely leads to the desired information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [146, 195]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"peru capital\" on Google, and the search results showed that Lima is the capital of Peru.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13262308062377949284_2.png",
"training_data/AITW/aitw_images/general/13262308062377949284_3.png",
"training_data/AITW/aitw_images/general/13262308062377949284_4.png"
] | 2,675
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>",
"role": "user"
},
{
"content": "Thought: Click PLAY to open the app for searching apartment rentals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [280, 1016]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_0.png"
] | 2,676
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Click PLAY to open the app for searching apartment rentals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [280, 1016]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Preferences button to access rental search settings for apartments in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [227, 995]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_0.png",
"training_data/AITW/aitw_images/general/13631136942144223616_1.png"
] | 2,677
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Click PLAY to open the app for searching apartment rentals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [280, 1016]}<image>Thought: Click the Preferences button to access rental search settings for apartments in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [227, 995]}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to access the search function for apartment rental information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 71]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_0.png",
"training_data/AITW/aitw_images/general/13631136942144223616_1.png",
"training_data/AITW/aitw_images/general/13631136942144223616_2.png"
] | 2,678
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Click the Preferences button to access rental search settings for apartments in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [227, 995]}<image>Thought: Click Search to access the search function for apartment rental information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 71]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search apps, web, and more\" to begin the search for apartment rent prices in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 68]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_1.png",
"training_data/AITW/aitw_images/general/13631136942144223616_2.png",
"training_data/AITW/aitw_images/general/13631136942144223616_3.png"
] | 2,679
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Click Search to access the search function for apartment rental information.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 71]}<image>Thought: Click on \"Search apps, web, and more\" to begin the search for apartment rent prices in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 68]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find the rental prices for a 2 bedroom apartment in Portland.\nAction: {\"action\": \"TYPE\", \"value\": \"How much does a 2 bedroom apartment rent for in Portland?\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_2.png",
"training_data/AITW/aitw_images/general/13631136942144223616_3.png",
"training_data/AITW/aitw_images/general/13631136942144223616_4.png"
] | 2,680
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Click on \"Search apps, web, and more\" to begin the search for apartment rent prices in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [122, 68]}<image>Thought: Type in the search bar to find the rental prices for a 2 bedroom apartment in Portland.\nAction: {\"action\": \"TYPE\", \"value\": \"How much does a 2 bedroom apartment rent for in Portland?\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"portland oregon\" to find relevant information about two-bedroom apartment rents in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [207, 162]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_3.png",
"training_data/AITW/aitw_images/general/13631136942144223616_4.png",
"training_data/AITW/aitw_images/general/13631136942144223616_5.png"
] | 2,681
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Portland?<image>Thought: Type in the search bar to find the rental prices for a 2 bedroom apartment in Portland.\nAction: {\"action\": \"TYPE\", \"value\": \"How much does a 2 bedroom apartment rent for in Portland?\", \"position\": null}<image>Thought: Click on \"portland oregon\" to find relevant information about two-bedroom apartment rents in Portland.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [207, 162]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the task by finding rent prices for 2 bedroom apartments in Portland using Google search results.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/13631136942144223616_4.png",
"training_data/AITW/aitw_images/general/13631136942144223616_5.png",
"training_data/AITW/aitw_images/general/13631136942144223616_6.png"
] | 2,682
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>",
"role": "user"
},
{
"content": "Thought: Click LOCATION to specify where I want to search for hotels in Austin.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 834]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_0.png"
] | 2,683
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Click LOCATION to specify where I want to search for hotels in Austin.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 834]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Samsung Galaxy Z Fold4 link to access the smartphone page instead of searching for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [229, 44]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_0.png",
"training_data/AITW/aitw_images/general/1314636206519724025_1.png"
] | 2,684
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Click LOCATION to specify where I want to search for hotels in Austin.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 834]}<image>Thought: Click the Samsung Galaxy Z Fold4 link to access the smartphone page instead of searching for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [229, 44]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"hotels in austin\" in the search bar to find relevant hotel options.\nAction: {\"action\": \"TYPE\", \"value\": \"hotels in austin\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_0.png",
"training_data/AITW/aitw_images/general/1314636206519724025_1.png",
"training_data/AITW/aitw_images/general/1314636206519724025_2.png"
] | 2,685
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Click the Samsung Galaxy Z Fold4 link to access the smartphone page instead of searching for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [229, 44]}<image>Thought: Type \"hotels in austin\" in the search bar to find relevant hotel options.\nAction: {\"action\": \"TYPE\", \"value\": \"hotels in austin\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"hotels in austin\" to begin the search for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 121]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_1.png",
"training_data/AITW/aitw_images/general/1314636206519724025_2.png",
"training_data/AITW/aitw_images/general/1314636206519724025_3.png"
] | 2,686
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Type \"hotels in austin\" in the search bar to find relevant hotel options.\nAction: {\"action\": \"TYPE\", \"value\": \"hotels in austin\", \"position\": null}<image>Thought: Click on \"hotels in austin\" to begin the search for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 121]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the link to access detailed information about the Five Star Hotels in Austin, TX.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [125, 336]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_2.png",
"training_data/AITW/aitw_images/general/1314636206519724025_3.png",
"training_data/AITW/aitw_images/general/1314636206519724025_4.png"
] | 2,687
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Click on \"hotels in austin\" to begin the search for hotels.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [120, 121]}<image>Thought: Click on the link to access detailed information about the Five Star Hotels in Austin, TX.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [125, 336]}<image>",
"role": "user"
},
{
"content": "Thought: Click Allow All to grant necessary permissions for hotel search functionality.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 978]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_3.png",
"training_data/AITW/aitw_images/general/1314636206519724025_4.png",
"training_data/AITW/aitw_images/general/1314636206519724025_5.png"
] | 2,688
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 hotels in Austin<image>Thought: Click on the link to access detailed information about the Five Star Hotels in Austin, TX.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [125, 336]}<image>Thought: Click Allow All to grant necessary permissions for hotel search functionality.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [256, 978]}<image>",
"role": "user"
},
{
"content": "Thought: The user has completed the search for hotels by finding relevant information on the displayed hotel page.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1314636206519724025_4.png",
"training_data/AITW/aitw_images/general/1314636206519724025_5.png",
"training_data/AITW/aitw_images/general/1314636206519724025_6.png"
] | 2,689
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>",
"role": "user"
},
{
"content": "Thought: Click CHAT to access a messaging app that might provide the current time for Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 494]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_0.png"
] | 2,690
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>Thought: Click CHAT to access a messaging app that might provide the current time for Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 494]}<image>",
"role": "user"
},
{
"content": "Thought: Check the website ments.com for a clock or information about the current time in Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 72]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_0.png",
"training_data/AITW/aitw_images/general/15610962330695713677_1.png"
] | 2,691
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>Thought: Click CHAT to access a messaging app that might provide the current time for Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [243, 494]}<image>Thought: Check the website ments.com for a clock or information about the current time in Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 72]}<image>",
"role": "user"
},
{
"content": "Thought: You need to input your query in the search bar. Type \"time in los angeles\" to search for the current time.\nAction: {\"action\": \"TYPE\", \"value\": \"time in los angeles\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_0.png",
"training_data/AITW/aitw_images/general/15610962330695713677_1.png",
"training_data/AITW/aitw_images/general/15610962330695713677_2.png"
] | 2,692
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>Thought: Check the website ments.com for a clock or information about the current time in Los Angeles.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [185, 72]}<image>Thought: You need to input your query in the search bar. Type \"time in los angeles\" to search for the current time.\nAction: {\"action\": \"TYPE\", \"value\": \"time in los angeles\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find information about the current time in Los Angeles.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_1.png",
"training_data/AITW/aitw_images/general/15610962330695713677_2.png",
"training_data/AITW/aitw_images/general/15610962330695713677_3.png"
] | 2,693
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>Thought: You need to input your query in the search bar. Type \"time in los angeles\" to search for the current time.\nAction: {\"action\": \"TYPE\", \"value\": \"time in los angeles\", \"position\": null}<image>Thought: Type in the search bar to find information about the current time in Los Angeles.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for the current time in Los Angeles.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_2.png",
"training_data/AITW/aitw_images/general/15610962330695713677_3.png",
"training_data/AITW/aitw_images/general/15610962330695713677_4.png"
] | 2,694
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: What time is it in Los Angeles?<image>Thought: Type in the search bar to find information about the current time in Los Angeles.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Press enter to initiate the search for the current time in Los Angeles.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You perform the operation to confirm that you successfully found the current time in Los Angeles displayed on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/15610962330695713677_3.png",
"training_data/AITW/aitw_images/general/15610962330695713677_4.png",
"training_data/AITW/aitw_images/general/15610962330695713677_5.png"
] | 2,695
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Houston?<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen where you can access various apps for apartment rentals.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1085258161929395035_0.png"
] | 2,696
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Houston?<image>Thought: Press home to return to the main screen where you can access various apps for apartment rentals.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the search results for apartment rentals in Houston.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1085258161929395035_0.png",
"training_data/AITW/aitw_images/general/1085258161929395035_1.png"
] | 2,697
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Houston?<image>Thought: Press home to return to the main screen where you can access various apps for apartment rentals.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the search results for apartment rentals in Houston.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more content related to apartment rentals in Houston.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1085258161929395035_0.png",
"training_data/AITW/aitw_images/general/1085258161929395035_1.png",
"training_data/AITW/aitw_images/general/1085258161929395035_2.png"
] | 2,698
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: How much does a 2 bedroom apartment rent for in Houston?<image>Thought: Scroll down to find the search results for apartment rentals in Houston.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more content related to apartment rentals in Houston.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You click Chrome to open the web browser for searching apartment rental prices in Houston.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 400]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/general/1085258161929395035_1.png",
"training_data/AITW/aitw_images/general/1085258161929395035_2.png",
"training_data/AITW/aitw_images/general/1085258161929395035_3.png"
] | 2,699
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.