messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the Rayovac AAA batteries listing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the selected item in your shopping list for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [395, 1110]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for \"rayovac triple a\" on eBay and found the item. You clicked on the first entry to view details. You then selected 'Buy It Now' to add the item to your cart, completing your task efficiently.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_8.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_9.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_10.png"
] | 9,800
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_0.png"
] | 9,801
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to open the web browser and access amazon.com to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1112]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_0.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_1.png"
] | 9,802
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome icon to open the web browser and access amazon.com to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1112]}<image>",
"role": "user"
},
{
"content": "Thought: The task cannot be completed because the user is on Target, not Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [598, 95]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_0.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_1.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_2.png"
] | 9,803
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click the Chrome icon to open the web browser and access amazon.com to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [482, 1112]}<image>Thought: The task cannot be completed because the user is on Target, not Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [598, 95]}<image>",
"role": "user"
},
{
"content": "Thought: You are currently on the Walmart cart page, so first, click BACK to return to Amazon. Then use the search function on Amazon to find the JBL Charge 4 speaker before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [48, 95]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_1.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_2.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_3.png"
] | 9,804
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: The task cannot be completed because the user is on Target, not Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [598, 95]}<image>Thought: You are currently on the Walmart cart page, so first, click BACK to return to Amazon. Then use the search function on Amazon to find the JBL Charge 4 speaker before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [48, 95]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon icon to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [621, 576]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_2.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_3.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_4.png"
] | 9,805
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: You are currently on the Walmart cart page, so first, click BACK to return to Amazon. Then use the search function on Amazon to find the JBL Charge 4 speaker before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [48, 95]}<image>Thought: Click the Amazon icon to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [621, 576]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search Amazon\" bar to prepare for entering the product name you want to view.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 256]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_3.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_4.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_5.png"
] | 9,806
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click the Amazon icon to navigate to the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [621, 576]}<image>Thought: Click the \"Search Amazon\" bar to prepare for entering the product name you want to view.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 256]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"jbl charge 4\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_4.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_5.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_6.png"
] | 9,807
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click the \"Search Amazon\" bar to prepare for entering the product name you want to view.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 256]}<image>Thought: Type \"jbl charge 4\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"jbl charge 4\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 328]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_5.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_6.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_7.png"
] | 9,808
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Type \"jbl charge 4\" in the search bar to find the product on Amazon.com.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl charge 4\", \"position\": null}<image>Thought: Click on \"jbl charge 4\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 328]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the JBL Charge 4 - Waterproof to view its details and add it to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [432, 739]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_6.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_7.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_8.png"
] | 9,809
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click on \"jbl charge 4\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 328]}<image>Thought: Click on the JBL Charge 4 - Waterproof to view its details and add it to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [432, 739]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X on the screen to close any pop-up notifications obstructing the view of adding JBL Charge 4 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1240]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_7.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_8.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_9.png"
] | 9,810
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click on the JBL Charge 4 - Waterproof to view its details and add it to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [432, 739]}<image>Thought: Click the X on the screen to close any pop-up notifications obstructing the view of adding JBL Charge 4 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1240]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the JBL Charge 4 details and the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_8.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_9.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_10.png"
] | 9,811
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click the X on the screen to close any pop-up notifications obstructing the view of adding JBL Charge 4 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1240]}<image>Thought: Scroll down to view the JBL Charge 4 details and the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the \"Add to Cart\" button for JBL Charge 4.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_9.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_10.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_11.png"
] | 9,812
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll down to view the JBL Charge 4 details and the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the \"Add to Cart\" button for JBL Charge 4.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more options related to the JBL Charge 4 speaker.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_10.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_11.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_12.png"
] | 9,813
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll down to find the \"Add to Cart\" button for JBL Charge 4.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options related to the JBL Charge 4 speaker.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate the JBL Charge 4 details and confirm it's available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_11.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_12.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_13.png"
] | 9,814
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll down to view more options related to the JBL Charge 4 speaker.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to locate the JBL Charge 4 details and confirm it's available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to find the JBL Charge 4 in the shopping cart section.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_12.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_13.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_14.png"
] | 9,815
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll down to locate the JBL Charge 4 details and confirm it's available for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to find the JBL Charge 4 in the shopping cart section.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to view the top of the page where the add-to-cart option is likely located.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_13.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_14.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_15.png"
] | 9,816
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll up to find the JBL Charge 4 in the shopping cart section.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view the top of the page where the add-to-cart option is likely located.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"See Similar Items\" to explore alternatives that can be shipped to the Netherlands.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 766]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_14.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_15.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_16.png"
] | 9,817
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Scroll up to view the top of the page where the add-to-cart option is likely located.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on \"See Similar Items\" to explore alternatives that can be shipped to the Netherlands.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 766]}<image>",
"role": "user"
},
{
"content": "Thought: Click Add to Cart to add JBL Charge 4 to the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 1251]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_15.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_16.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_17.png"
] | 9,818
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click on \"See Similar Items\" to explore alternatives that can be shipped to the Netherlands.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 766]}<image>Thought: Click Add to Cart to add JBL Charge 4 to the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 1251]}<image>",
"role": "user"
},
{
"content": "Thought: Click Add to Cart to add the JBL Charge 4 speaker to the shopping cart on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [559, 1254]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_16.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_17.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_18.png"
] | 9,819
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.com. Add jbl charge 4 to the cart on amazon.com<image>Thought: Click Add to Cart to add JBL Charge 4 to the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [352, 1251]}<image>Thought: Click Add to Cart to add the JBL Charge 4 speaker to the shopping cart on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [559, 1254]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for \"jbl charge 4\" in the search bar. You have viewed the product details of the JBL Charge 4 speaker. You navigated to add it to your shopping cart ensuring it's ready for purchase. The task is now complete with the item added to your cart on Amazon.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16516413206170596231_17.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_18.png",
"training_data/AITW/aitw_images/webshopping/16516413206170596231_19.png"
] | 9,820
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay\" in the search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_0.png"
] | 9,821
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"ebay\" in the search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook\" into the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_0.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_1.png"
] | 9,822
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"ebay\" in the search bar to initiate a search for the website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay\", \"position\": null}<image>Thought: Type \"macbook\" into the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ebay search result to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 186]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_0.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_1.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_2.png"
] | 9,823
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"macbook\" into the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Click the ebay search result to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 186]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the eBay link to access the website where I can search for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 336]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_1.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_2.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_3.png"
] | 9,824
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the ebay search result to navigate to the eBay website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 186]}<image>Thought: Click on the eBay link to access the website where I can search for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 336]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search for anything\" field to start entering your search term.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 281]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_2.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_3.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_4.png"
] | 9,825
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on the eBay link to access the website where I can search for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 336]}<image>Thought: Click the \"Search for anything\" field to start entering your search term.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 281]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the sign-in prompt and proceed with searching for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1027]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_3.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_4.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_5.png"
] | 9,826
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"Search for anything\" field to start entering your search term.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 281]}<image>Thought: Click the X to close the sign-in prompt and proceed with searching for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1027]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search for anything\" field to begin inputting search terms.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 265]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_4.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_5.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_6.png"
] | 9,827
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the X to close the sign-in prompt and proceed with searching for \"macbook.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [683, 1027]}<image>Thought: Click the \"Search for anything\" field to begin inputting search terms.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 265]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook\" into the search bar to begin finding the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_5.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_6.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_7.png"
] | 9,828
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"Search for anything\" field to begin inputting search terms.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 265]}<image>Thought: Type \"macbook\" into the search bar to begin finding the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_6.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_7.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_8.png"
] | 9,829
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"macbook\" into the search bar to begin finding the product.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook\", \"position\": null}<image>Thought: Type \"macbook\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Laptops & Netbooks\" to narrow down the search results for MacBook options specifically.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 423]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_7.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_8.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_9.png"
] | 9,830
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"macbook\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"\", \"position\": null}<image>Thought: Click on \"Laptops & Netbooks\" to narrow down the search results for MacBook options specifically.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 423]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"3.40GHz\" to view details of the MacBook Pro you are interested in purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 673]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_8.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_9.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_10.png"
] | 9,831
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Laptops & Netbooks\" to narrow down the search results for MacBook options specifically.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 423]}<image>Thought: Click on \"3.40GHz\" to view details of the MacBook Pro you are interested in purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 673]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view additional entries for \"macbook\" and find the first one to select.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_9.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_10.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_11.png"
] | 9,832
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"3.40GHz\" to view details of the MacBook Pro you are interested in purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [333, 673]}<image>Thought: Scroll down to view additional entries for \"macbook\" and find the first one to select.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Was\" to view the previous price and determine if the current listing is a good deal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 1095]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_10.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_11.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_12.png"
] | 9,833
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view additional entries for \"macbook\" and find the first one to select.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"Was\" to view the previous price and determine if the current listing is a good deal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 1095]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more information about the first MacBook entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_11.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_12.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_13.png"
] | 9,834
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Was\" to view the previous price and determine if the current listing is a good deal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 1095]}<image>Thought: Scroll down to view more information about the first MacBook entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Add to cart to save the first MacBook entry for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 616]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_12.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_13.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_14.png"
] | 9,835
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more information about the first MacBook entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click Add to cart to save the first MacBook entry for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 616]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View cart\" to see the items I have added before completing the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 616]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_13.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_14.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_15.png"
] | 9,836
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"macbook\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click Add to cart to save the first MacBook entry for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [351, 616]}<image>Thought: Click \"View cart\" to see the items I have added before completing the purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 616]}<image>",
"role": "user"
},
{
"content": "Thought: You have accessed the shopping cart to review your items after successfully adding the MacBook.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15081017856329933208_14.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_15.png",
"training_data/AITW/aitw_images/webshopping/15081017856329933208_16.png"
] | 9,837
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Click the CHAT option to seek assistance for clearing the cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 471]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_0.png"
] | 9,838
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click the CHAT option to seek assistance for clearing the cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 471]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the link to access the secure checkout page, possibly to clear or manage items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 38]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_0.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_1.png"
] | 9,839
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click the CHAT option to seek assistance for clearing the cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 471]}<image>Thought: Click on the link to access the secure checkout page, possibly to clear or manage items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 38]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" in the address bar to navigate to Walmart's website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_0.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_1.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_2.png"
] | 9,840
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click on the link to access the secure checkout page, possibly to clear or manage items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [111, 38]}<image>Thought: Type \"walmart.com\" in the address bar to navigate to Walmart's website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the walmart.com link to navigate to the Walmart website and access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 91]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_1.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_2.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_3.png"
] | 9,841
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Type \"walmart.com\" in the address bar to navigate to Walmart's website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click the walmart.com link to navigate to the Walmart website and access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 91]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to access the items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 80]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_2.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_3.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_4.png"
] | 9,842
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click the walmart.com link to navigate to the Walmart website and access your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 91]}<image>Thought: Click SHOPPING CART to access the items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 80]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the items in the cart and check for the Logitech G Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_3.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_4.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_5.png"
] | 9,843
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click SHOPPING CART to access the items in the cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [240, 80]}<image>Thought: Scroll down to view the items in the cart and check for the Logitech G Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You would click Remove to eliminate items from the cart before adding new ones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [36, 443]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_4.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_5.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_6.png"
] | 9,844
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Scroll down to view the items in the cart and check for the Logitech G Pro.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You would click Remove to eliminate items from the cart before adding new ones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [36, 443]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to begin searching for the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 46]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_5.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_6.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_7.png"
] | 9,845
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: You would click Remove to eliminate items from the cart before adding new ones.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [36, 443]}<image>Thought: Click the search bar to begin searching for the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 46]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g pro\" in the search bar to find the product on Walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \" logitech g pro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_6.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_7.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_8.png"
] | 9,846
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click the search bar to begin searching for the Logitech G Pro.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 46]}<image>Thought: Type \"logitech g pro\" in the search bar to find the product on Walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \" logitech g pro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"logitech g pro\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 131]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_7.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_8.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_9.png"
] | 9,847
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Type \"logitech g pro\" in the search bar to find the product on Walmart.com.\nAction: {\"action\": \"TYPE\", \"value\": \" logitech g pro\", \"position\": null}<image>Thought: Click on \"logitech g pro\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 131]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for the Logitech G Pro on Walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_8.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_9.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_10.png"
] | 9,848
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click on \"logitech g pro\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [66, 131]}<image>Thought: Scroll down to view more search results for the Logitech G Pro on Walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products related to \"logitech g pro\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_9.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_10.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_11.png"
] | 9,849
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Scroll down to view more search results for the Logitech G Pro on Walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products related to \"logitech g pro\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the STAR to favorite or save the Logitech G Pro product for easy access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 400]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_10.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_11.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_12.png"
] | 9,850
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Scroll down to view more products related to \"logitech g pro\" on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the STAR to favorite or save the Logitech G Pro product for easy access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 400]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the Logitech G Pro in your shopping cart on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 506]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_11.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_12.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_13.png"
] | 9,851
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart.com. Add logitech g pro to the cart on walmart.com<image>Thought: Click the STAR to favorite or save the Logitech G Pro product for easy access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 400]}<image>Thought: Click \"Add to cart\" to include the Logitech G Pro in your shopping cart on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 506]}<image>",
"role": "user"
},
{
"content": "Thought: You confirmed the addition of Logitech G Pro to the cart by reviewing the “Added to cart” message on the screen.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15764217741526287731_12.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_13.png",
"training_data/AITW/aitw_images/webshopping/15764217741526287731_14.png"
] | 9,852
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and access the home screen for further navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_0.png"
] | 9,853
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and access the home screen for further navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 1219]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_0.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_1.png"
] | 9,854
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and access the home screen for further navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 1219]}<image>",
"role": "user"
},
{
"content": "Thought: Enter \"razer huntsman\" in the search box to find the product on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 100]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_0.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_1.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_2.png"
] | 9,855
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the Chrome app to open it for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 1219]}<image>Thought: Enter \"razer huntsman\" in the search box to find the product on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 100]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" in the search bar to find the website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_1.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_2.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_3.png"
] | 9,856
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Enter \"razer huntsman\" in the search box to find the product on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [502, 100]}<image>Thought: Type \"walmart\" in the search bar to find the website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Retail company\" link to access Walmart's official website and initiate your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 336]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_2.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_3.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_4.png"
] | 9,857
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"walmart\" in the search bar to find the website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click on the \"Retail company\" link to access Walmart's official website and initiate your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 336]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Walmart link to access the store's website and start searching for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [277, 860]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_3.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_4.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_5.png"
] | 9,858
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the \"Retail company\" link to access Walmart's official website and initiate your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 336]}<image>Thought: Click on the Walmart link to access the store's website and start searching for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [277, 860]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to enter \"razer huntsman.\" Next, click on the relevant search suggestion to view product details. Then, find and click the first entry to access its page. Finally, click the add to cart button to purchase it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 204]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_4.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_5.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_6.png"
] | 9,859
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the Walmart link to access the store's website and start searching for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [277, 860]}<image>Thought: Click on the search bar to enter \"razer huntsman.\" Next, click on the relevant search suggestion to view product details. Then, find and click the first entry to access its page. Finally, click the add to cart button to purchase it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 204]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer huntsman\" in the search bar to find the desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_5.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_6.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_7.png"
] | 9,860
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the search bar to enter \"razer huntsman.\" Next, click on the relevant search suggestion to view product details. Then, find and click the first entry to access its page. Finally, click the add to cart button to purchase it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 204]}<image>Thought: Type \"razer huntsman\" in the search bar to find the desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search for \"razer huntsman\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [548, 220]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_6.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_7.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_8.png"
] | 9,861
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"razer huntsman\" in the search bar to find the desired product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer huntsman\", \"position\": null}<image>Thought: Click the magnifying glass to initiate the search for \"razer huntsman\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [548, 220]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked the +Add button to add the Razer Huntsman Mini keyboard to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [530, 1202]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_7.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_8.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_9.png"
] | 9,862
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for razer huntsman on walmart, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to initiate the search for \"razer huntsman\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [548, 220]}<image>Thought: You clicked the +Add button to add the Razer Huntsman Mini keyboard to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [530, 1202]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"razer huntsman\" on Walmart's website. You selected the first entry from the search results, indicating a successful choice. You added the item to your cart, and you confirmed that the intended task is complete now.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2918333587115692641_8.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_9.png",
"training_data/AITW/aitw_images/webshopping/2918333587115692641_10.png"
] | 9,863
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and start a new search for \"razer blade.\"\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_0.png"
] | 9,864
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to return to the main screen and start a new search for \"razer blade.\"\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to open the app drawer and access the web browser for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 1009]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_0.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_1.png"
] | 9,865
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Press home to return to the main screen and start a new search for \"razer blade.\"\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the NAV BAR CIRCLE to open the app drawer and access the web browser for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 1009]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Costco to initiate a search for products on their website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [253, 138]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_0.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_1.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_2.png"
] | 9,866
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the NAV BAR CIRCLE to open the app drawer and access the web browser for your search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 1009]}<image>Thought: Click on Costco to initiate a search for products on their website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [253, 138]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco link to access the website and search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 515]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_1.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_2.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_3.png"
] | 9,867
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on Costco to initiate a search for products on their website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [253, 138]}<image>Thought: Click on the Costco link to access the website and search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 515]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Warehouses button to navigate to warehouse deals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_2.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_3.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_4.png"
] | 9,868
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Costco link to access the website and search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [44, 515]}<image>Thought: Click on the Warehouses button to navigate to warehouse deals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to find related products on Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_3.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_4.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_5.png"
] | 9,869
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the Warehouses button to navigate to warehouse deals.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [320, 283]}<image>Thought: Type \"razer blade\" in the search bar to find related products on Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the MAGNIFYING GLASS to initiate the search process for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [473, 280]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_4.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_5.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_6.png"
] | 9,870
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"razer blade\" in the search bar to find related products on Costco.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>Thought: Click the MAGNIFYING GLASS to initiate the search process for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [473, 280]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_5.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_6.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_7.png"
] | 9,871
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the MAGNIFYING GLASS to initiate the search process for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [473, 280]}<image>Thought: Scroll down to view the search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add\" to include the selected Razer Blade laptop in your cart for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 816]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_6.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_7.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_8.png"
] | 9,872
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on costco, select the first entry, add it to the cart, then select checkout.<image>Thought: Scroll down to view the search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add\" to include the selected Razer Blade laptop in your cart for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 816]}<image>",
"role": "user"
},
{
"content": "Thought: You searched for \"razer blade\" and found the product in the results. You selected the first entry to view its details. After reviewing the product, you added it to your cart successfully. Finally, you proceeded to checkout to complete your purchase, confirming that all operations were executed correctly and efficiently.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1622903358768098879_7.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_8.png",
"training_data/AITW/aitw_images/webshopping/1622903358768098879_9.png"
] | 9,873
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate the Newegg app or website for accessing the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_0.png"
] | 9,874
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Scroll down to locate the Newegg app or website for accessing the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Chrome\" app to access the internet for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 392]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_0.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_1.png"
] | 9,875
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Scroll down to locate the Newegg app or website for accessing the shopping cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Chrome\" app to access the internet for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 392]}<image>",
"role": "user"
},
{
"content": "Thought: You need to sign in to view the shopping cart, so click the link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [297, 66]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_0.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_1.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_2.png"
] | 9,876
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Click the \"Chrome\" app to access the internet for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [274, 392]}<image>Thought: You need to sign in to view the shopping cart, so click the link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [297, 66]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" in the search bar to navigate to the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_1.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_2.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_3.png"
] | 9,877
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: You need to sign in to view the shopping cart, so click the link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [297, 66]}<image>Thought: Type \"newegg.com\" in the search bar to navigate to the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to load the Newegg website and view the shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_2.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_3.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_4.png"
] | 9,878
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Type \"newegg.com\" in the search bar to navigate to the Newegg website.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Press enter to load the Newegg website and view the shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon at the top right corner to view your cart details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 137]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_3.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_4.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_5.png"
] | 9,879
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Press enter to load the Newegg website and view the shopping cart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the SHOPPING CART icon at the top right corner to view your cart details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 137]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to check if there are hidden items in the shopping cart or additional options available.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_4.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_5.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_6.png"
] | 9,880
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Click the SHOPPING CART icon at the top right corner to view your cart details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 137]}<image>Thought: Scroll up to check if there are hidden items in the shopping cart or additional options available.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You likely want to access your account options by clicking on the person icon for the shopping cart view.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [529, 351]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_5.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_6.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_7.png"
] | 9,881
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on newegg.<image>Thought: Scroll up to check if there are hidden items in the shopping cart or additional options available.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: You likely want to access your account options by clicking on the person icon for the shopping cart view.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [529, 351]}<image>",
"role": "user"
},
{
"content": "Thought: You have viewed the shopping cart on Newegg, which shows it is empty.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/234290695083523057_6.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_7.png",
"training_data/AITW/aitw_images/webshopping/234290695083523057_8.png"
] | 9,882
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>",
"role": "user"
},
{
"content": "Thought: Click the YouTube icon to open the app for possible guidance on finding Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 505]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_0.png"
] | 9,883
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click the YouTube icon to open the app for possible guidance on finding Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 505]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the blue arrow indicating the \"Add to Cart\" button to add the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 31]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_0.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_1.png"
] | 9,884
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click the YouTube icon to open the app for possible guidance on finding Acer Predator.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 505]}<image>Thought: Click on the blue arrow indicating the \"Add to Cart\" button to add the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 31]}<image>",
"role": "user"
},
{
"content": "Thought: Click on eBay to access the website where I can add products to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 544]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_0.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_1.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_2.png"
] | 9,885
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click on the blue arrow indicating the \"Add to Cart\" button to add the desired item.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [107, 31]}<image>Thought: Click on eBay to access the website where I can add products to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 544]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the eBay link to access the website and begin searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 177]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_1.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_2.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_3.png"
] | 9,886
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click on eBay to access the website where I can add products to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 544]}<image>Thought: Click on the eBay link to access the website and begin searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 177]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for anything\" to access the input field for entering the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 99]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_2.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_3.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_4.png"
] | 9,887
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click on the eBay link to access the website and begin searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 177]}<image>Thought: Click on \"Search for anything\" to access the input field for entering the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 99]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer predator\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_3.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_4.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_5.png"
] | 9,888
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click on \"Search for anything\" to access the input field for entering the product name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [70, 99]}<image>Thought: Type \"acer predator\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"acer predator\" in the search results to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 206]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_4.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_5.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_6.png"
] | 9,889
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Type \"acer predator\" in the search bar to find the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: Click on \"acer predator\" in the search results to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 206]}<image>",
"role": "user"
},
{
"content": "Thought: Click STAR to save the Acer Predator listing for quick access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 309]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_5.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_6.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_7.png"
] | 9,890
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click on \"acer predator\" in the search results to select the desired item for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 206]}<image>Thought: Click STAR to save the Acer Predator listing for quick access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 309]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Acer Predator laptop before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_6.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_7.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_8.png"
] | 9,891
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Click STAR to save the Acer Predator listing for quick access later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [79, 309]}<image>Thought: Scroll down to view more details about the Acer Predator laptop before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to save the Acer Predator for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [127, 439]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_7.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_8.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_9.png"
] | 9,892
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add acer predator to the cart on ebay.com<image>Thought: Scroll down to view more details about the Acer Predator laptop before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to save the Acer Predator for later purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [127, 439]}<image>",
"role": "user"
},
{
"content": "Thought: You likely selected \"Buy It Now\" on the Acer Predator item to add it directly to your cart. The operation indicates the purchase was finalized successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14582578449249495307_8.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_9.png",
"training_data/AITW/aitw_images/webshopping/14582578449249495307_10.png"
] | 9,893
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current app and return to the main screen for easier navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_0.png"
] | 9,894
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>Thought: Press home to exit the current app and return to the main screen for easier navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome icon to access the browser for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_0.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_1.png"
] | 9,895
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>Thought: Press home to exit the current app and return to the main screen for easier navigation.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome icon to access the browser for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome icon to open the browser for browsing Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_0.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_1.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_2.png"
] | 9,896
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>Thought: Click the Chrome icon to access the browser for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}<image>Thought: Click on the Chrome icon to open the browser for browsing Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the website link to access Newegg where the Logitech G910 is listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 91]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_1.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_2.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_3.png"
] | 9,897
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>Thought: Click on the Chrome icon to open the browser for browsing Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [500, 1218]}<image>Thought: Click on the website link to access Newegg where the Logitech G910 is listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 91]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" in the web address bar to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_2.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_3.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_4.png"
] | 9,898
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add logitech g910 to the cart on newegg, then select checkout.<image>Thought: Click on the website link to access Newegg where the Logitech G910 is listed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 91]}<image>Thought: Type \"newegg.com\" in the web address bar to access the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue link to navigate to the Newegg website for purchasing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [149, 231]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5093068361932409078_3.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_4.png",
"training_data/AITW/aitw_images/webshopping/5093068361932409078_5.png"
] | 9,899
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.