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: Add razer nari to the cart on bestbuy.com<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome browser icon to open it for accessing bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 855]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_0.png"
] | 7,600
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Click the Chrome browser icon to open it for accessing bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 855]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen because the sign-in is required to access the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_0.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_1.png"
] | 7,601
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Click the Chrome browser icon to open it for accessing bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [365, 855]}<image>Thought: Press back to return to the previous screen because the sign-in is required to access the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Search to open the search bar for entering the item name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 201]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_0.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_1.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_2.png"
] | 7,602
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Press back to return to the previous screen because the sign-in is required to access the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Click Search to open the search bar for entering the item name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 201]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer nari\" in the search bar to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_1.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_2.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_3.png"
] | 7,603
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Click Search to open the search bar for entering the item name.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [216, 201]}<image>Thought: Type \"razer nari\" in the search bar to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"razer nari\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 219]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_2.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_3.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_4.png"
] | 7,604
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Type \"razer nari\" in the search bar to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer nari\", \"position\": null}<image>Thought: Click on \"razer nari\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 219]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate the Razer Nari product details on Best Buy's search results page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_3.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_4.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_5.png"
] | 7,605
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Click on \"razer nari\" to select the product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 219]}<image>Thought: Scroll down to locate the Razer Nari product details on Best Buy's search results page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button on the Razer Nari Ultimate headset to begin the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 516]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_4.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_5.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_6.png"
] | 7,606
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Scroll down to locate the Razer Nari product details on Best Buy's search results page.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button on the Razer Nari Ultimate headset to begin the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 516]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Add to Cart\" to purchase the Razer Nari Ultimate headset displayed on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 585]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_5.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_6.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_7.png"
] | 7,607
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add razer nari to the cart on bestbuy.com<image>Thought: Click the \"Add to Cart\" button on the Razer Nari Ultimate headset to begin the purchase process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [404, 516]}<image>Thought: Click on \"Add to Cart\" to purchase the Razer Nari Ultimate headset displayed on the screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 585]}<image>",
"role": "user"
},
{
"content": "Thought: You likely tapped \"Add to Cart\" for Razer Nari, indicating your interest in purchasing it. The screen confirms the item is now in your cart, so the task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/5452161781188126910_6.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_7.png",
"training_data/AITW/aitw_images/webshopping/5452161781188126910_8.png"
] | 7,608
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the main screen and access the Amazon app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_0.png"
] | 7,609
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Press home to return to the main screen and access the Amazon app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Open the Google app to access the internet for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 1279]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_0.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_1.png"
] | 7,610
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Press home to return to the main screen and access the Amazon app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Open the Google app to access the internet for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 1279]}<image>",
"role": "user"
},
{
"content": "Thought: Click the GOOGLE icon to open the browser for accessing amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 1274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_0.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_1.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_2.png"
] | 7,611
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Open the Google app to access the internet for Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 1279]}<image>Thought: Click the GOOGLE icon to open the browser for accessing amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 1274]}<image>",
"role": "user"
},
{
"content": "Thought: Click Google to access the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 1284]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_1.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_2.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_3.png"
] | 7,612
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the GOOGLE icon to open the browser for accessing amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 1274]}<image>Thought: Click Google to access the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 1284]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" in the search bar to access the website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_2.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_3.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_4.png"
] | 7,613
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click Google to access the web browser for searching Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [129, 1284]}<image>Thought: Type \"amazon.com\" in the search bar to access the website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"razer blade\" on amazon.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_3.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_4.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_5.png"
] | 7,614
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Type \"amazon.com\" in the search bar to access the website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Press enter to initiate the search for \"razer blade\" on amazon.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the shopping cart icon to access the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [663, 156]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_4.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_5.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_6.png"
] | 7,615
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Press enter to initiate the search for \"razer blade\" on amazon.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the shopping cart icon to access the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [663, 156]}<image>",
"role": "user"
},
{
"content": "Thought: Click the picture to view more options related to the item, allowing further actions like adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [581, 1087]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_5.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_6.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_7.png"
] | 7,616
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the shopping cart icon to access the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [663, 156]}<image>Thought: Click the picture to view more options related to the item, allowing further actions like adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [581, 1087]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access the cart and clear its contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 156]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_6.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_7.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_8.png"
] | 7,617
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the picture to view more options related to the item, allowing further actions like adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [581, 1087]}<image>Thought: Click the SHOPPING CART icon to access the cart and clear its contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 156]}<image>",
"role": "user"
},
{
"content": "Thought: Click the DELETE option to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 922]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_7.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_8.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_9.png"
] | 7,618
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the SHOPPING CART icon to access the cart and clear its contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 156]}<image>Thought: Click the DELETE option to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 922]}<image>",
"role": "user"
},
{
"content": "Thought: Click Deliver to Netherlands to ensure the shipping location is set correctly before adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_8.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_9.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_10.png"
] | 7,619
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the DELETE option to remove the item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [60, 922]}<image>Thought: Click Deliver to Netherlands to ensure the shipping location is set correctly before adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 225]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon's site.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_9.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_10.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_11.png"
] | 7,620
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click Deliver to Netherlands to ensure the shipping location is set correctly before adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 225]}<image>Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon's site.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You want to search for \"razer blade\" in the search bar, so press enter to generate results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_10.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_11.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_12.png"
] | 7,621
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Type \"razer blade\" in the search bar to find the desired product on Amazon's site.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>Thought: You want to search for \"razer blade\" in the search bar, so press enter to generate results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the product listing with the GeForce RTX 3080 to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 557]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_11.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_12.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_13.png"
] | 7,622
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: You want to search for \"razer blade\" in the search bar, so press enter to generate results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the product listing with the GeForce RTX 3080 to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 557]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Razer Blade laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_12.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_13.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_14.png"
] | 7,623
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Click the product listing with the GeForce RTX 3080 to view more details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [394, 557]}<image>Thought: Scroll down to view more details about the Razer Blade laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to add the \"razer blade\" to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 1009]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_13.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_14.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_15.png"
] | 7,624
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on amazon.com. Add \"razer blade\" to the cart on amazon.com<image>Thought: Scroll down to view more details about the Razer Blade laptop.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to Cart\" button to add the \"razer blade\" to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [336, 1009]}<image>",
"role": "user"
},
{
"content": "Thought: You have completed the task as indicated by successfully clearing the shopping cart and adding the \"Razer Blade\" to it.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17127723925673537445_14.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_15.png",
"training_data/AITW/aitw_images/webshopping/17127723925673537445_16.png"
] | 7,625
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>",
"role": "user"
},
{
"content": "Thought: You would 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/12670854990106383874_0.png"
] | 7,626
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: You would 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: Press home to return to the main screen and exit the current app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_0.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_1.png"
] | 7,627
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: You would press home to exit the current application and return to the main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Press home to return to the main screen and exit the current app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access notifications or messages regarding the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [503, 1207]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_0.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_1.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_2.png"
] | 7,628
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Press home to return to the main screen and exit the current app.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the ENVELOPE icon to access notifications or messages regarding the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [503, 1207]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to access your email for order details related to the cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_1.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_2.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_3.png"
] | 7,629
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE icon to access notifications or messages regarding the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [503, 1207]}<image>Thought: Click the ENVELOPE to access your email for order details related to the cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to open the email app, as it may contain Amazon-related notifications or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1196]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_2.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_3.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_4.png"
] | 7,630
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE to access your email for order details related to the cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}<image>Thought: Click the ENVELOPE icon to open the email app, as it may contain Amazon-related notifications or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1196]}<image>",
"role": "user"
},
{
"content": "Thought: You would click the ENVELOPE to open your email app for possible Amazon notifications.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_3.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_4.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_5.png"
] | 7,631
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE icon to open the email app, as it may contain Amazon-related notifications or updates.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1196]}<image>Thought: You would click the ENVELOPE to open your email app for possible Amazon notifications.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open the email app, as that's where order notifications might be.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1186]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_4.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_5.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_6.png"
] | 7,632
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: You would click the ENVELOPE to open your email app for possible Amazon notifications.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [487, 1199]}<image>Thought: Click the ENVELOPE to open the email app, as that's where order notifications might be.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1186]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE icon to access your emails, which may contain order confirmations related to the amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1189]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_5.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_6.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_7.png"
] | 7,633
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE to open the email app, as that's where order notifications might be.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1186]}<image>Thought: Click the ENVELOPE icon to access your emails, which may contain order confirmations related to the amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1189]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open the messaging app for possible communication about your Amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_6.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_7.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_8.png"
] | 7,634
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE icon to access your emails, which may contain order confirmations related to the amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [506, 1189]}<image>Thought: Click the ENVELOPE to open the messaging app for possible communication about your Amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open the email application for account verification or assistance with Amazon's cart clearing process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_7.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_8.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_9.png"
] | 7,635
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE to open the messaging app for possible communication about your Amazon cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>Thought: Click the ENVELOPE to open the email application for account verification or assistance with Amazon's cart clearing process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to access the email app, likely for order confirmation or notifications regarding the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_8.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_9.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_10.png"
] | 7,636
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE to open the email application for account verification or assistance with Amazon's cart clearing process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>Thought: Click the ENVELOPE to access the email app, likely for order confirmation or notifications regarding the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>",
"role": "user"
},
{
"content": "Thought: Click the sign-in page to access my Amazon account and proceed with clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 87]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_9.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_10.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_11.png"
] | 7,637
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the ENVELOPE to access the email app, likely for order confirmation or notifications regarding the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [497, 1207]}<image>Thought: Click the sign-in page to access my Amazon account and proceed with clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 87]}<image>",
"role": "user"
},
{
"content": "Thought: You need to sign in to your Amazon account, so you click on the Amazon Sign-In link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 181]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_10.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_11.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_12.png"
] | 7,638
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click the sign-in page to access my Amazon account and proceed with clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [366, 87]}<image>Thought: You need to sign in to your Amazon account, so you click on the Amazon Sign-In link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 181]}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen and navigate to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_11.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_12.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_13.png"
] | 7,639
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: You need to sign in to your Amazon account, so you click on the Amazon Sign-In link.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [106, 181]}<image>Thought: Press back to return to the previous screen and navigate to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click Delete to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 604]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_12.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_13.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_14.png"
] | 7,640
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Press back to return to the previous screen and navigate to the cart.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Click Delete to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 604]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Delete\" to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 597]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_13.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_14.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_15.png"
] | 7,641
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on amazon.<image>Thought: Click Delete to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [311, 604]}<image>Thought: Click \"Delete\" to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 597]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates the user successfully cleared the cart, and the message confirms an item was removed.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12670854990106383874_14.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_15.png",
"training_data/AITW/aitw_images/webshopping/12670854990106383874_16.png"
] | 7,642
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Press home to return to the device's main screen and access the eBay app for searching.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_0.png"
] | 7,643
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Press home to return to the device's main screen and access the eBay app for searching.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Google Chrome app to start browsing for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1207]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_0.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_1.png"
] | 7,644
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Press home to return to the device's main screen and access the eBay app for searching.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Google Chrome app to start browsing for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1207]}<image>",
"role": "user"
},
{
"content": "Thought: Accept the terms to proceed with using Chrome for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 1376]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_0.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_1.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_2.png"
] | 7,645
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the Google Chrome app to start browsing for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [504, 1207]}<image>Thought: Accept the terms to proceed with using Chrome for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 1376]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Yes, I'm in\" button to proceed with syncing for better personalized search results on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 1382]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_1.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_2.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_3.png"
] | 7,646
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Accept the terms to proceed with using Chrome for searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [370, 1376]}<image>Thought: Click the \"Yes, I'm in\" button to proceed with syncing for better personalized search results on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 1382]}<image>",
"role": "user"
},
{
"content": "Thought: Click on eBay to navigate to the website for searching items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [451, 748]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_2.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_3.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_4.png"
] | 7,647
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"Yes, I'm in\" button to proceed with syncing for better personalized search results on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [585, 1382]}<image>Thought: Click on eBay to navigate to the website for searching items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [451, 748]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search for anything\" box to input your search query for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 299]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_3.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_4.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_5.png"
] | 7,648
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on eBay to navigate to the website for searching items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [451, 748]}<image>Thought: Click the \"Search for anything\" box to input your search query for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 299]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"acer nitro\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_4.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_5.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_6.png"
] | 7,649
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"Search for anything\" box to input your search query for \"acer nitro.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [246, 299]}<image>Thought: Type \"acer nitro\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Decline All\" to dismiss the cookie consent popup and proceed with the search for \"acer nitro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 1292]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_5.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_6.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_7.png"
] | 7,650
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"acer nitro\" in the search bar to initiate the product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"acer nitro\", \"position\": null}<image>Thought: Click on \"Decline All\" to dismiss the cookie consent popup and proceed with the search for \"acer nitro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 1292]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate the search for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 281]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_6.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_7.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_8.png"
] | 7,651
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Decline All\" to dismiss the cookie consent popup and proceed with the search for \"acer nitro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [321, 1292]}<image>Thought: Click the magnifying glass to initiate the search for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 281]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Acer Nitro entry to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 695]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_7.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_8.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_9.png"
] | 7,652
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to initiate the search for \"acer nitro\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 281]}<image>Thought: Click the Acer Nitro entry to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 695]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results and select the first entry for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_8.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_9.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_10.png"
] | 7,653
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the Acer Nitro entry to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 695]}<image>Thought: Scroll down to view more search results and select the first entry for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press back to return to the previous screen and select a different item or verify the list of entries.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_9.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_10.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_11.png"
] | 7,654
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results and select the first entry for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Press back to return to the previous screen and select a different item or verify the list of entries.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the entry for \"Acer Nitro 5 15.6\\\" Laptop RTX 3060\" to view product details and proceed with purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [643, 1097]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_10.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_11.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_12.png"
] | 7,655
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Press back to return to the previous screen and select a different item or verify the list of entries.\nAction: {\"action\": \"PRESS BACK\", \"value\": null, \"position\": null}<image>Thought: Click the entry for \"Acer Nitro 5 15.6\\\" Laptop RTX 3060\" to view product details and proceed with purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [643, 1097]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the first item listed for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_11.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_12.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_13.png"
] | 7,656
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the entry for \"Acer Nitro 5 15.6\\\" Laptop RTX 3060\" to view product details and proceed with purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [643, 1097]}<image>Thought: Scroll down to view more details about the first item listed for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"X\" to close any pop-up or unwanted overlay, ensuring full access to the main content.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [37, 1394]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_12.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_13.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_14.png"
] | 7,657
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the first item listed for \"acer nitro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"X\" to close any pop-up or unwanted overlay, ensuring full access to the main content.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [37, 1394]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to proceed with saving the selected Acer Nitro laptop for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [446, 1190]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_13.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_14.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_15.png"
] | 7,658
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"acer nitro\" on ebay, select the first entry, and add it to the cart.<image>Thought: Click the \"X\" to close any pop-up or unwanted overlay, ensuring full access to the main content.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [37, 1394]}<image>Thought: Click \"Add to cart\" to proceed with saving the selected Acer Nitro laptop for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [446, 1190]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully searched for \"acer nitro\" and found the relevant listing. You selected the first entry that matched your search criteria. After reviewing the details, you proceeded to add it to your cart by clicking on the appropriate option. Now that you've completed all necessary steps, you confirmed that your task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2039935267625039698_14.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_15.png",
"training_data/AITW/aitw_images/webshopping/2039935267625039698_16.png"
] | 7,659
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to launch the app for newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 1042]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_0.png"
] | 7,660
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Click the NAV BAR CIRCLE to launch the app for newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 1042]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg\" into the search bar to find the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_0.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_1.png"
] | 7,661
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Click the NAV BAR CIRCLE to launch the app for newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 1042]}<image>Thought: Type \"newegg\" into the search bar to find the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the NewEgg link to access the shopping website and begin your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [191, 165]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_0.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_1.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_2.png"
] | 7,662
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Type \"newegg\" into the search bar to find the Newegg website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg\", \"position\": null}<image>Thought: Click on the NewEgg link to access the shopping website and begin your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [191, 165]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Newegg.com\" link to access the website and proceed with shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 362]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_1.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_2.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_3.png"
] | 7,663
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Click on the NewEgg link to access the shopping website and begin your task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [191, 165]}<image>Thought: Click the \"Newegg.com\" link to access the website and proceed with shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 362]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Keywords, Model #, Item #\" search bar to enter your search term. Type \"sony triple a\" to find the desired product. Press enter to submit your search and view the results. Scroll down through the listings to locate the first entry that matches your criteria. Click on that first entry for more details before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 186]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_2.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_3.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_4.png"
] | 7,664
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Click the \"Newegg.com\" link to access the website and proceed with shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 362]}<image>Thought: Click on the \"Keywords, Model #, Item #\" search bar to enter your search term. Type \"sony triple a\" to find the desired product. Press enter to submit your search and view the results. Scroll down through the listings to locate the first entry that matches your criteria. Click on that first entry for more details before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 186]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"sony triple a\" in the search bar to find the desired items on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"sony triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_3.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_4.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_5.png"
] | 7,665
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the shopping cart on newegg. Search for \"sony triple a\" on newegg, select the first entry, and add it to the cart.<image>Thought: Click on the \"Keywords, Model #, Item #\" search bar to enter your search term. Type \"sony triple a\" to find the desired product. Press enter to submit your search and view the results. Scroll down through the listings to locate the first entry that matches your criteria. Click on that first entry for more details before adding it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 186]}<image>Thought: Type \"sony triple a\" in the search bar to find the desired items on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"sony triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Access the search bar in the GUI to enter \"sony triple a\" for product search. Upon completing the search, confirm that products related to \"sony triple a\" are displayed, indicating successful input. Since task completion status is noted as complete, it implies all necessary steps were successfully executed as required on Newegg's platform.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6686222314104088478_4.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_5.png",
"training_data/AITW/aitw_images/webshopping/6686222314104088478_6.png"
] | 7,666
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the Google Photos app and return to the main screen for shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_0.png"
] | 7,667
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Press home to exit the Google Photos app and return to the main screen for shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click GOOGLE to open the browser and search for the JBL Flip 4 on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 956]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_0.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_1.png"
] | 7,668
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Press home to exit the Google Photos app and return to the main screen for shopping.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click GOOGLE to open the browser and search for the JBL Flip 4 on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 956]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"target\" in the search bar to find the target shopping app.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_0.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_1.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_2.png"
] | 7,669
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click GOOGLE to open the browser and search for the JBL Flip 4 on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 956]}<image>Thought: Type \"target\" in the search bar to find the target shopping app.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_1.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_2.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_3.png"
] | 7,670
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Type \"target\" in the search bar to find the target shopping app.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>Thought: Press enter to execute the search for \"target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Target Online - Target Online\" to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [92, 467]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_2.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_3.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_4.png"
] | 7,671
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Press enter to execute the search for \"target\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on \"Target Online - Target Online\" to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [92, 467]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search bar to enter your desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_3.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_4.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_5.png"
] | 7,672
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click on \"Target Online - Target Online\" to access the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [92, 467]}<image>Thought: Click the Search bar to enter your desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 274]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"jbl flip 4\" in the search bar to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl flip 4\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_4.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_5.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_6.png"
] | 7,673
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click the Search bar to enter your desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [72, 274]}<image>Thought: Type \"jbl flip 4\" in the search bar to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl flip 4\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"jbl flip 4\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_5.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_6.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_7.png"
] | 7,674
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Type \"jbl flip 4\" in the search bar to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"jbl flip 4\", \"position\": null}<image>Thought: Press enter to execute the search for \"jbl flip 4\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the JBL Flip 4 product on the Target webpage.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_6.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_7.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_8.png"
] | 7,675
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Press enter to execute the search for \"jbl flip 4\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the JBL Flip 4 product on the Target webpage.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the JBL Flip 4 in the search results since it's not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_7.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_8.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_9.png"
] | 7,676
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Scroll down to find the JBL Flip 4 product on the Target webpage.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the JBL Flip 4 in the search results since it's not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the JBL Flip 4 in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_8.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_9.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_10.png"
] | 7,677
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Scroll down to find the JBL Flip 4 in the search results since it's not visible on the screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the JBL Flip 4 in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" on the JBL Flip 4 option to proceed with purchasing the speaker.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 625]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_9.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_10.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_11.png"
] | 7,678
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Scroll down to find the JBL Flip 4 in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" on the JBL Flip 4 option to proceed with purchasing the speaker.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 625]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to add JBL Pulse 4 to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 473]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_10.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_11.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_12.png"
] | 7,679
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click \"Add to cart\" on the JBL Flip 4 option to proceed with purchasing the speaker.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 625]}<image>Thought: Click the \"Add to cart\" button to add JBL Pulse 4 to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 473]}<image>",
"role": "user"
},
{
"content": "Thought: Click Decline coverage to opt out of the protection plan for the JBL Pulse 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 989]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_11.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_12.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_13.png"
] | 7,680
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click the \"Add to cart\" button to add JBL Pulse 4 to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [276, 473]}<image>Thought: Click Decline coverage to opt out of the protection plan for the JBL Pulse 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 989]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to proceed with checkout after adding JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_12.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_13.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_14.png"
] | 7,681
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click Decline coverage to opt out of the protection plan for the JBL Pulse 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [347, 989]}<image>Thought: Click on the SHOPPING CART icon to proceed with checkout after adding JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Sign in to check out\" button to proceed with the checkout process for the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 985]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_13.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_14.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_15.png"
] | 7,682
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add jbl flip 4 to the cart on target, then select checkout.<image>Thought: Click on the SHOPPING CART icon to proceed with checkout after adding JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [494, 67]}<image>Thought: Click on the \"Sign in to check out\" button to proceed with the checkout process for the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 985]}<image>",
"role": "user"
},
{
"content": "Thought: Recognize that the task of adding the JBL Flip 4 to your cart on Target is completed successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/9593763985222715476_14.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_15.png",
"training_data/AITW/aitw_images/webshopping/9593763985222715476_16.png"
] | 7,683
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click on the Chrome app icon to access the web browser and navigate to newegg.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [375, 884]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_0.png"
] | 7,684
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click on the Chrome app icon to access the web browser and navigate to newegg.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [375, 884]}<image>",
"role": "user"
},
{
"content": "Thought: Click Sign in to access my account on newegg.com for managing the shopping cart and checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 79]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_0.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_1.png"
] | 7,685
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click on the Chrome app icon to access the web browser and navigate to newegg.com for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [375, 884]}<image>Thought: Click Sign in to access my account on newegg.com for managing the shopping cart and checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 79]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"newegg.com\" in the search bar to navigate to the desired website for emptying the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_0.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_1.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_2.png"
] | 7,686
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click Sign in to access my account on newegg.com for managing the shopping cart and checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [305, 79]}<image>Thought: Type \"newegg.com\" in the search bar to navigate to the desired website for emptying the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to navigate to the Newegg website after typing the URL in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_1.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_2.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_3.png"
] | 7,687
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Type \"newegg.com\" in the search bar to navigate to the desired website for emptying the shopping cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Press enter to navigate to the Newegg website after typing the URL in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the pop-up and access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [467, 323]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_2.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_3.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_4.png"
] | 7,688
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Press enter to navigate to the Newegg website after typing the URL in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the X to close the pop-up and access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [467, 323]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the country selection popup and proceed with the shopping cart operation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 666]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_3.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_4.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_5.png"
] | 7,689
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click the X to close the pop-up and access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [467, 323]}<image>Thought: Click the X to close the country selection popup and proceed with the shopping cart operation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 666]}<image>",
"role": "user"
},
{
"content": "Thought: Select \"United States\" to ensure you can shop from the correct region on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [464, 356]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_4.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_5.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_6.png"
] | 7,690
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click the X to close the country selection popup and proceed with the shopping cart operation.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 666]}<image>Thought: Select \"United States\" to ensure you can shop from the correct region on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [464, 356]}<image>",
"role": "user"
},
{
"content": "Thought: Click DONE to confirm the selected country for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 927]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_5.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_6.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_7.png"
] | 7,691
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Select \"United States\" to ensure you can shop from the correct region on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [464, 356]}<image>Thought: Click DONE to confirm the selected country for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 927]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Item # link to access the product details for \"lg ultragear.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [326, 212]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_6.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_7.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_8.png"
] | 7,692
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click DONE to confirm the selected country for shopping on Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 927]}<image>Thought: Click the Item # link to access the product details for \"lg ultragear.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [326, 212]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"lg ultragear\" into the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lg ultragear\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_7.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_8.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_9.png"
] | 7,693
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click the Item # link to access the product details for \"lg ultragear.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [326, 212]}<image>Thought: Type \"lg ultragear\" into the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lg ultragear\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to initiate the search for \"lg ultragear\" in the search bar on newegg.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_8.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_9.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_10.png"
] | 7,694
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Type \"lg ultragear\" into the search bar to find the product on newegg.com.\nAction: {\"action\": \"TYPE\", \"value\": \"lg ultragear\", \"position\": null}<image>Thought: Press enter to initiate the search for \"lg ultragear\" in the search bar on newegg.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"LG UltraGear\" to view product details and ensure it’s the correct item to add.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [147, 686]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_9.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_10.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_11.png"
] | 7,695
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Press enter to initiate the search for \"lg ultragear\" in the search bar on newegg.com.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click on the \"LG UltraGear\" to view product details and ensure it’s the correct item to add.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [147, 686]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"ADD TO CART\" to add the LG UltraGear to your shopping cart on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [284, 1041]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_10.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_11.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_12.png"
] | 7,696
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click on the \"LG UltraGear\" to view product details and ensure it’s the correct item to add.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [147, 686]}<image>Thought: Click \"ADD TO CART\" to add the LG UltraGear to your shopping cart on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [284, 1041]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X on the protection plan popup to dismiss it and access the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [511, 320]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_11.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_12.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_13.png"
] | 7,697
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click \"ADD TO CART\" to add the LG UltraGear to your shopping cart on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [284, 1041]}<image>Thought: Click the X on the protection plan popup to dismiss it and access the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [511, 320]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to view the contents of your cart and proceed with emptying it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [26, 1033]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_12.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_13.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_14.png"
] | 7,698
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on newegg.com. Add \"lg ultragear\" to the cart on newegg.com, then select checkout.<image>Thought: Click the X on the protection plan popup to dismiss it and access the main page.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [511, 320]}<image>Thought: Click the SHOPPING CART icon to view the contents of your cart and proceed with emptying it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [26, 1033]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"SECURE CHECKOUT\" button to proceed with the checkout process on the cart screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [232, 1015]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/751714942438914651_13.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_14.png",
"training_data/AITW/aitw_images/webshopping/751714942438914651_15.png"
] | 7,699
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.