messages
listlengths 2
200
| images
listlengths 1
3
| custom_id
int64 0
66.2k
⌀ |
|---|---|---|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for a dining table on crateandbarrel.com<image>Thought: Click PLAY to open the app needed for searching dining tables on crateandbarrel.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [237, 958]}<image>Thought: Type \"crateandbarrel.com\" into the search bar to navigate to the website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"crateandbarrel.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You entered your search query and pressed enter to see relevant results for \"crateandbarrel.com.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_0.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_1.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_2.png"
] | 9,700
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a dining table on crateandbarrel.com<image>Thought: Type \"crateandbarrel.com\" into the search bar to navigate to the website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"crateandbarrel.com\", \"position\": null}<image>Thought: You entered your search query and pressed enter to see relevant results for \"crateandbarrel.com.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You want to learn more about the limited time rewards offer, so you click on \"LIMITED TIME ONLY.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [184, 184]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_1.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_2.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_3.png"
] | 9,701
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a dining table on crateandbarrel.com<image>Thought: You entered your search query and pressed enter to see relevant results for \"crateandbarrel.com.\"\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: You want to learn more about the limited time rewards offer, so you click on \"LIMITED TIME ONLY.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [184, 184]}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"dining table\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_2.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_3.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_4.png"
] | 9,702
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a dining table on crateandbarrel.com<image>Thought: You want to learn more about the limited time rewards offer, so you click on \"LIMITED TIME ONLY.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [184, 184]}<image>Thought: Press enter to execute the search for \"dining table\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dining table\" in the search box to find relevant products on crateandbarrel.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dining table\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_3.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_4.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_5.png"
] | 9,703
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a dining table on crateandbarrel.com<image>Thought: Press enter to execute the search for \"dining table\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Type \"dining table\" in the search box to find relevant products on crateandbarrel.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dining table\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"dining table\" on crateandbarrel.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 175]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_4.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_5.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_6.png"
] | 9,704
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 a dining table on crateandbarrel.com<image>Thought: Type \"dining table\" in the search box to find relevant products on crateandbarrel.com.\nAction: {\"action\": \"TYPE\", \"value\": \"dining table\", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"dining table\" on crateandbarrel.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 175]}<image>",
"role": "user"
},
{
"content": "Thought: Status indicates task complete, confirming the user successfully searched for dining tables on the website.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16479768864976703980_5.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_6.png",
"training_data/AITW/aitw_images/webshopping/16479768864976703980_7.png"
] | 9,705
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to open the shopping app or browser for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1148]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_0.png"
] | 9,706
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the ENVELOPE to open the shopping app or browser for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1148]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to search for \"macbook air\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 65]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_0.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_1.png"
] | 9,707
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the ENVELOPE to open the shopping app or browser for Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [492, 1148]}<image>Thought: Click the magnifying glass to search for \"macbook air\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 65]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart\" to navigate to the desired website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_0.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_1.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_2.png"
] | 9,708
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the magnifying glass to search for \"macbook air\" on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [447, 65]}<image>Thought: Type \"walmart\" to navigate to the desired website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Walmart\" to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 275]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_1.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_2.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_3.png"
] | 9,709
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Type \"walmart\" to navigate to the desired website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click on \"Walmart\" to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 275]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Walmart® Official Site - Free two-day shipping\" to access the Walmart online store for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 634]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_2.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_3.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_4.png"
] | 9,710
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"Walmart\" to access the Walmart website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [126, 275]}<image>Thought: Click on \"Walmart® Official Site - Free two-day shipping\" to access the Walmart online store for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 634]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 173]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_3.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_4.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_5.png"
] | 9,711
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"Walmart® Official Site - Free two-day shipping\" to access the Walmart online store for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 634]}<image>Thought: Click the SHOPPING CART icon to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 173]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search everything\" to initiate a product search for the \"MacBook Air.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [306, 166]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_4.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_5.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_6.png"
] | 9,712
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the SHOPPING CART icon to access the cart and manage items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [654, 173]}<image>Thought: Click on \"Search everything\" to initiate a product search for the \"MacBook Air.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [306, 166]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"macbook air\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_5.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_6.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_7.png"
] | 9,713
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"Search everything\" to initiate a product search for the \"MacBook Air.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [306, 166]}<image>Thought: Type \"macbook air\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"macbook air\" to view the product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 379]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_6.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_7.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_8.png"
] | 9,714
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Type \"macbook air\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"macbook air\", \"position\": null}<image>Thought: Click on \"macbook air\" to view the product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 379]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove items from the shopping cart, allowing a fresh start for adding new products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [679, 1087]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_7.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_8.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_9.png"
] | 9,715
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click on \"macbook air\" to view the product details and add it to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 379]}<image>Thought: Click the X to remove items from the shopping cart, allowing a fresh start for adding new products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [679, 1087]}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue \"+ Add\" button to add the MacBook Air to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [550, 1068]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_8.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_9.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_10.png"
] | 9,716
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the X to remove items from the shopping cart, allowing a fresh start for adding new products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [679, 1087]}<image>Thought: Click the blue \"+ Add\" button to add the MacBook Air to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [550, 1068]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"+ Add\" button to include the MacBook Air in your shopping cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [534, 1079]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_9.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_10.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_11.png"
] | 9,717
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the blue \"+ Add\" button to add the MacBook Air to the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [550, 1068]}<image>Thought: Click the \"+ Add\" button to include the MacBook Air in your shopping cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [534, 1079]}<image>",
"role": "user"
},
{
"content": "Thought: Click SHOPPING CART to review the current items before proceeding with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 176]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_10.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_11.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_12.png"
] | 9,718
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click the \"+ Add\" button to include the MacBook Air in your shopping cart on walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [534, 1079]}<image>Thought: Click SHOPPING CART to review the current items before proceeding with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 176]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue to checkout\" to proceed with the purchasing process after adding the MacBook Air to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 1270]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_11.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_12.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_13.png"
] | 9,719
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add \"macbook air\" to the cart on walmart.com, then select checkout.<image>Thought: Click SHOPPING CART to review the current items before proceeding with the checkout process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [662, 176]}<image>Thought: Click \"Continue to checkout\" to proceed with the purchasing process after adding the MacBook Air to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [331, 1270]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully emptied the shopping cart and proceeded to checkout. The action fulfills your task on walmart.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1157891181884689092_12.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_13.png",
"training_data/AITW/aitw_images/webshopping/1157891181884689092_14.png"
] | 9,720
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>",
"role": "user"
},
{
"content": "Thought: Press home to exit the current application in order to access the Amazon app for viewing the shopping cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_0.png"
] | 9,721
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>Thought: Press home to exit the current application in order to access the Amazon app for viewing the shopping cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Amazon app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 539]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_0.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_1.png"
] | 9,722
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>Thought: Press home to exit the current application in order to access the Amazon app for viewing the shopping cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the Amazon app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 539]}<image>",
"role": "user"
},
{
"content": "Thought: Click the URL in the address bar to navigate to the desired shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [189, 58]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_0.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_1.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_2.png"
] | 9,723
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>Thought: Click on the Amazon app icon to open it and access the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [263, 539]}<image>Thought: Click the URL in the address bar to navigate to the desired shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [189, 58]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Amazon.com link to navigate to the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 217]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_1.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_2.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_3.png"
] | 9,724
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>Thought: Click the URL in the address bar to navigate to the desired shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [189, 58]}<image>Thought: Click the Amazon.com link to navigate to the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 217]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access your items for purchase. This action is necessary to view what you've selected.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 135]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_2.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_3.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_4.png"
] | 9,725
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on amazon.<image>Thought: Click the Amazon.com link to navigate to the shopping site.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 217]}<image>Thought: Click the SHOPPING CART icon to access your items for purchase. This action is necessary to view what you've selected.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [374, 135]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully accessed the shopping cart view on Amazon, confirming that the task is complete.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/12550075643350022671_3.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_4.png",
"training_data/AITW/aitw_images/webshopping/12550075643350022671_5.png"
] | 9,726
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: The executed operation does not align with the intended task of interacting with Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 483]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_0.png"
] | 9,727
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible: The executed operation does not align with the intended task of interacting with Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 483]}<image>",
"role": "user"
},
{
"content": "Thought: Click the THREE DOTS to access additional options for managing items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 38]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_0.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_1.png"
] | 9,728
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Status task impossible: The executed operation does not align with the intended task of interacting with Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [171, 483]}<image>Thought: Click the THREE DOTS to access additional options for managing items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 38]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"olecina\" tab to access Newegg for clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 100]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_0.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_1.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_2.png"
] | 9,729
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the THREE DOTS to access additional options for managing items in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [225, 38]}<image>Thought: Click on the \"olecina\" tab to access Newegg for clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 100]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"SHOPPING CART\" to access the items in your cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 548]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_1.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_2.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_3.png"
] | 9,730
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the \"olecina\" tab to access Newegg for clearing the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 100]}<image>Thought: Click \"SHOPPING CART\" to access the items in your cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 548]}<image>",
"role": "user"
},
{
"content": "Thought: Click the HEART icon to save the item for later instead of deleting it from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [19, 291]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_2.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_3.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_4.png"
] | 9,731
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click \"SHOPPING CART\" to access the items in your cart for clearing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [17, 548]}<image>Thought: Click the HEART icon to save the item for later instead of deleting it from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [19, 291]}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to access the search function for finding Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [211, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_3.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_4.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_5.png"
] | 9,732
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the HEART icon to save the item for later instead of deleting it from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [19, 291]}<image>Thought: Click the magnifying glass to access the search function for finding Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [211, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"alienware aurora\" in the search bar to find the product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware aurora\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_4.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_5.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_6.png"
] | 9,733
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the magnifying glass to access the search function for finding Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [211, 67]}<image>Thought: Type \"alienware aurora\" in the search bar to find the product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware aurora\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the first entry to view the product details for the Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 98]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_5.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_6.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_7.png"
] | 9,734
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Type \"alienware aurora\" in the search bar to find the product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"alienware aurora\", \"position\": null}<image>Thought: Click on the first entry to view the product details for the Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 98]}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry \"Dell Alienware Aurora R\" to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 434]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_6.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_7.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_8.png"
] | 9,735
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click on the first entry to view the product details for the Alienware Aurora.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [28, 98]}<image>Thought: Click the first entry \"Dell Alienware Aurora R\" to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 434]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"ADD TO CART\" button to include the selected Alienware Aurora item in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 552]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_7.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_8.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_9.png"
] | 9,736
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 newegg. Search for alienware aurora on newegg, select the first entry, add it to the cart, then select checkout.<image>Thought: Click the first entry \"Dell Alienware Aurora R\" to view its details and proceed with adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [170, 434]}<image>Thought: Click the \"ADD TO CART\" button to include the selected Alienware Aurora item in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [132, 552]}<image>",
"role": "user"
},
{
"content": "Thought: The task is marked as complete after successfully adding Alienware Aurora to the cart and proceeding to checkout.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6688075436887177470_8.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_9.png",
"training_data/AITW/aitw_images/webshopping/6688075436887177470_10.png"
] | 9,737
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: You need to start from the home screen to access the Costco app for your search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_0.png"
] | 9,738
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: You need to start from the home screen to access the Costco app for your search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You mistakenly clicked on the CHAT icon instead of opening a web browser to search for \"dell xps\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 528]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_0.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_1.png"
] | 9,739
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: You need to start from the home screen to access the Costco app for your search.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: You mistakenly clicked on the CHAT icon instead of opening a web browser to search for \"dell xps\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 528]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked on a link expecting to find the Razer product, but now you're faced with an error page indicating the site is malfunctioning. You should consider navigating back to your original task of searching for \"dell xps\" on Costco.com instead of remaining blocked by this redirect issue.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 67]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_0.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_1.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_2.png"
] | 9,740
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: You mistakenly clicked on the CHAT icon instead of opening a web browser to search for \"dell xps\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [250, 528]}<image>Thought: You clicked on a link expecting to find the Razer product, but now you're faced with an error page indicating the site is malfunctioning. You should consider navigating back to your original task of searching for \"dell xps\" on Costco.com instead of remaining blocked by this redirect issue.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 67]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Costco.com entry to navigate to the website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 370]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_1.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_2.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_3.png"
] | 9,741
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: You clicked on a link expecting to find the Razer product, but now you're faced with an error page indicating the site is malfunctioning. You should consider navigating back to your original task of searching for \"dell xps\" on Costco.com instead of remaining blocked by this redirect issue.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [159, 67]}<image>Thought: Click on the Costco.com entry to navigate to the website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 370]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Search button to initiate a search for Dell XPS on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 286]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_2.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_3.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_4.png"
] | 9,742
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: Click on the Costco.com entry to navigate to the website for searching.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [90, 370]}<image>Thought: Click the Search button to initiate a search for Dell XPS on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 286]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell xps\" into the search bar to initiate a product search on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_3.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_4.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_5.png"
] | 9,743
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: Click the Search button to initiate a search for Dell XPS on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [162, 286]}<image>Thought: Type \"dell xps\" into the search bar to initiate a product search on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to submit the search for \"dell xps\" on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [360, 279]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_4.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_5.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_6.png"
] | 9,744
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 dell xps on costco.com, select the first entry, and add it to the cart.<image>Thought: Type \"dell xps\" into the search bar to initiate a product search on Costco's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>Thought: Click the magnifying glass to submit the search for \"dell xps\" on Costco's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [360, 279]}<image>",
"role": "user"
},
{
"content": "Thought: You likely entered \"dell xps\" in the search bar on costco.com to find the product. You then selected the first entry from the search results to view more details about it. After reviewing, you added it to your cart for future purchase, completing your task successfully.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1880175216815446730_5.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_6.png",
"training_data/AITW/aitw_images/webshopping/1880175216815446730_7.png"
] | 9,745
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Click the MIC to use voice search for adding \"logitech g pro\" to the cart on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [489, 1162]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_0.png"
] | 9,746
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the MIC to use voice search for adding \"logitech g pro\" to the cart on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [489, 1162]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible because the user is on Costco.com, not Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 92]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_0.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_1.png"
] | 9,747
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the MIC to use voice search for adding \"logitech g pro\" to the cart on amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [489, 1162]}<image>Thought: Status task impossible because the user is on Costco.com, not Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 92]}<image>",
"role": "user"
},
{
"content": "Thought: Click the highlighted Amazon.com icon to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 332]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_0.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_1.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_2.png"
] | 9,748
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Status task impossible because the user is on Costco.com, not Amazon.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 92]}<image>Thought: Click the highlighted Amazon.com icon to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 332]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to access the cart contents for clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 172]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_1.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_2.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_3.png"
] | 9,749
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the highlighted Amazon.com icon to access the website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 332]}<image>Thought: Click the SHOPPING CART icon to access the cart contents for clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 172]}<image>",
"role": "user"
},
{
"content": "Thought: You would click \"Delete\" to remove the item from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 958]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_2.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_3.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_4.png"
] | 9,750
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the SHOPPING CART icon to access the cart contents for clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [666, 172]}<image>Thought: You would click \"Delete\" to remove the item from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 958]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Deliver to Netherlands\" option to ensure the correct delivery location for the shopping cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [230, 265]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_3.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_4.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_5.png"
] | 9,751
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: You would click \"Delete\" to remove the item from your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [296, 958]}<image>Thought: Click the \"Deliver to Netherlands\" option to ensure the correct delivery location for the shopping cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [230, 265]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g pro\" in the search bar to find the desired item on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_4.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_5.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_6.png"
] | 9,752
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the \"Deliver to Netherlands\" option to ensure the correct delivery location for the shopping cart items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [230, 265]}<image>Thought: Type \"logitech g pro\" in the search bar to find the desired item on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to initiate a search for \"logitech g pro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_5.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_6.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_7.png"
] | 9,753
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Type \"logitech g pro\" in the search bar to find the desired item on Amazon.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g pro \", \"position\": null}<image>Thought: Click the magnifying glass to initiate a search for \"logitech g pro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 274]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g pro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_6.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_7.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_8.png"
] | 9,754
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the magnifying glass to initiate a search for \"logitech g pro\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [660, 274]}<image>Thought: Scroll down to view more search results for \"logitech g pro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results for \"logitech g pro\" on amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_7.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_8.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_9.png"
] | 9,755
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view more search results for \"logitech g pro.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more results for \"logitech g pro\" on amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the Logitech MX Anywhere to view the product details before adding \"logitech g pro\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [677, 1187]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_8.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_9.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_10.png"
] | 9,756
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view more results for \"logitech g pro\" on amazon.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Logitech MX Anywhere to view the product details before adding \"logitech g pro\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [677, 1187]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view products to add \"logitech g pro\" to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_9.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_10.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_11.png"
] | 9,757
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click the Logitech MX Anywhere to view the product details before adding \"logitech g pro\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [677, 1187]}<image>Thought: Scroll down to view products to add \"logitech g pro\" to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products and find \"Logitech G Pro\" in the shopping list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_10.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_11.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_12.png"
] | 9,758
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view products to add \"logitech g pro\" to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products and find \"Logitech G Pro\" in the shopping list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"RGB\" label to select a specific product variant or view more options related to RGB features. This action helps narrow down the search for \"logitech g pro\" products that match user preferences.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 887]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_11.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_12.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_13.png"
] | 9,759
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view more products and find \"Logitech G Pro\" in the shopping list.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"RGB\" label to select a specific product variant or view more options related to RGB features. This action helps narrow down the search for \"logitech g pro\" products that match user preferences.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 887]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details and options for the \"logitech g pro\" item in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_12.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_13.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_14.png"
] | 9,760
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Click on the \"RGB\" label to select a specific product variant or view more options related to RGB features. This action helps narrow down the search for \"logitech g pro\" products that match user preferences.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [516, 887]}<image>Thought: Scroll down to view more details and options for the \"logitech g pro\" item in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the price and details for the \"logitech g pro\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_13.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_14.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_15.png"
] | 9,761
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view more details and options for the \"logitech g pro\" item in the search results.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the price and details for the \"logitech g pro\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the selected product, \"logitech g pro,\" in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 1218]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_14.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_15.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_16.png"
] | 9,762
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 \"logitech g pro\" to the cart on amazon.com<image>Thought: Scroll down to view the price and details for the \"logitech g pro\" product.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to include the selected product, \"logitech g pro,\" in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [376, 1218]}<image>",
"role": "user"
},
{
"content": "Thought: You performed the operation to clear the shopping cart on amazon.com and added \"logitech g pro\" successfully. Since the status is task complete, you confirm that these actions have been executed as intended without any issues.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/1992192181862937336_15.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_16.png",
"training_data/AITW/aitw_images/webshopping/1992192181862937336_17.png"
] | 9,763
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>",
"role": "user"
},
{
"content": "Thought: Click the PLAY icon to open the app menu and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 556]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_0.png"
] | 9,764
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>Thought: Click the PLAY icon to open the app menu and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 556]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Accept & continue\" to proceed past the welcome screen and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 632]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_0.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_1.png"
] | 9,765
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>Thought: Click the PLAY icon to open the app menu and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [131, 556]}<image>Thought: Click \"Accept & continue\" to proceed past the welcome screen and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 632]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"No thanks\" to dismiss the sync prompt and proceed to access the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [61, 629]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_0.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_1.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_2.png"
] | 9,766
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>Thought: Click \"Accept & continue\" to proceed past the welcome screen and access Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 632]}<image>Thought: Click \"No thanks\" to dismiss the sync prompt and proceed to access the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [61, 629]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Amazon.co.. to access the Amazon app or website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 384]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_1.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_2.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_3.png"
] | 9,767
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>Thought: Click \"No thanks\" to dismiss the sync prompt and proceed to access the shopping cart on Amazon.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [61, 629]}<image>Thought: Click on Amazon.co.. to access the Amazon app or website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 384]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 122]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_2.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_3.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_4.png"
] | 9,768
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Show the shopping cart on amazon.<image>Thought: Click on Amazon.co.. to access the Amazon app or website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [251, 384]}<image>Thought: Click the SHOPPING CART to view items added for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [377, 122]}<image>",
"role": "user"
},
{
"content": "Thought: The user successfully navigated to the Amazon shopping cart by completing the necessary steps, confirming that they can view their cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/16294947975567164603_3.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_4.png",
"training_data/AITW/aitw_images/webshopping/16294947975567164603_5.png"
] | 9,769
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: You click on the Walmart app to access your shopping cart and perform actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 909]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_0.png"
] | 9,770
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: You click on the Walmart app to access your shopping cart and perform actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 909]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to access the items currently in your cart for editing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 142]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_0.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_1.png"
] | 9,771
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: You click on the Walmart app to access your shopping cart and perform actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 909]}<image>Thought: Click the SHOPPING CART to access the items currently in your cart for editing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 142]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to input \"logitech g933\" for adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 255]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_0.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_1.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_2.png"
] | 9,772
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Click the SHOPPING CART to access the items currently in your cart for editing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [480, 142]}<image>Thought: Click the search bar to input \"logitech g933\" for adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 255]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"logitech g933\" into the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_1.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_2.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_3.png"
] | 9,773
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Click the search bar to input \"logitech g933\" for adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [239, 255]}<image>Thought: Type \"logitech g933\" into the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"logitech g933\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [74, 251]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_2.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_3.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_4.png"
] | 9,774
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Type \"logitech g933\" into the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"logitech g933\", \"position\": null}<image>Thought: Click the \"logitech g933\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [74, 251]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g933\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_3.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_4.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_5.png"
] | 9,775
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Click the \"logitech g933\" option to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [74, 251]}<image>Thought: Scroll down to view more search results for \"logitech g933\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products and locate the \"Logitech G933\" headset for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_4.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_5.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_6.png"
] | 9,776
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Scroll down to view more search results for \"logitech g933\" and find the item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more products and locate the \"Logitech G933\" headset for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"logitech g933\" to find available options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_5.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_6.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_7.png"
] | 9,777
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Scroll down to view more products and locate the \"Logitech G933\" headset for adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for \"logitech g933\" to find available options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the \"Logitech G933\" headset options and select the desired one for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_6.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_7.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_8.png"
] | 9,778
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Scroll down to view more search results for \"logitech g933\" to find available options.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to find the \"Logitech G933\" headset options and select the desired one for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"+ Add\" button to add the cable to the cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 890]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_7.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_8.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_9.png"
] | 9,779
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Scroll down to find the \"Logitech G933\" headset options and select the desired one for adding to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"+ Add\" button to add the cable to the cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 890]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"SHOPPING CART\" to view current items and proceed to clear the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 157]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_8.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_9.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_10.png"
] | 9,780
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Click on the \"+ Add\" button to add the cable to the cart for checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [393, 890]}<image>Thought: Click \"SHOPPING CART\" to view current items and proceed to clear the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 157]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Continue to checkout\" to proceed with purchasing the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 985]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_9.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_10.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_11.png"
] | 9,781
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on walmart. Add \"logitech g933\" to the cart on walmart, then select checkout.<image>Thought: Click \"SHOPPING CART\" to view current items and proceed to clear the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 157]}<image>Thought: Click \"Continue to checkout\" to proceed with purchasing the item in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [254, 985]}<image>",
"role": "user"
},
{
"content": "Thought: You successfully completed the task of clearing and checking out the cart on Walmart, indicating all steps were performed correctly.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2772237867774387299_10.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_11.png",
"training_data/AITW/aitw_images/webshopping/2772237867774387299_12.png"
] | 9,782
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>",
"role": "user"
},
{
"content": "Thought: Click the NAV BAR CIRCLE to access the app drawer and find the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 1347]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_0.png"
] | 9,783
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Click the NAV BAR CIRCLE to access the app drawer and find the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 1347]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Amazon icon to open the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_0.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_1.png"
] | 9,784
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Click the NAV BAR CIRCLE to access the app drawer and find the Amazon app.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [342, 1347]}<image>Thought: Click on the Amazon icon to open the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Amazon.com link to access the website and search for the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 454]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_0.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_1.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_2.png"
] | 9,785
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Click on the Amazon icon to open the Amazon website for shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 283]}<image>Thought: Click on the Amazon.com link to access the website and search for the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 454]}<image>",
"role": "user"
},
{
"content": "Thought: Click on 'Basics' to explore products in that category to find the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 246]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_1.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_2.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_3.png"
] | 9,786
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Click on the Amazon.com link to access the website and search for the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [167, 454]}<image>Thought: Click on 'Basics' to explore products in that category to find the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 246]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"amazon.com\" to navigate to the website for adding items to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_2.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_3.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_4.png"
] | 9,787
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Click on 'Basics' to explore products in that category to find the JBL Flip 4.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [198, 246]}<image>Thought: Type \"amazon.com\" to navigate to the website for adding items to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click amazon.com/code to navigate to the desired page for adding the JBL Flip 4 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 306]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_3.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_4.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_5.png"
] | 9,788
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [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 amazon.com<image>Thought: Type \"amazon.com\" to navigate to the website for adding items to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon.com\", \"position\": null}<image>Thought: Click amazon.com/code to navigate to the desired page for adding the JBL Flip 4 to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [259, 306]}<image>",
"role": "user"
},
{
"content": "Thought: You have successfully completed the task by adding the JBL Flip 4 to your cart on Amazon.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13662990762371734856_4.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_5.png",
"training_data/AITW/aitw_images/webshopping/13662990762371734856_6.png"
] | 9,789
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the ENVELOPE to access the email or messaging app for communication purposes before searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1168]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_0.png"
] | 9,790
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the ENVELOPE to access the email or messaging app for communication purposes before searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1168]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: The user cannot complete their task of searching for items on eBay due to the action taken on Amazon instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 105]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_0.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_1.png"
] | 9,791
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the ENVELOPE to access the email or messaging app for communication purposes before searching on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1168]}<image>Thought: Status task impossible: The user cannot complete their task of searching for items on eBay due to the action taken on Amazon instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 105]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay.com\" into the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_0.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_1.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_2.png"
] | 9,792
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Status task impossible: The user cannot complete their task of searching for items on eBay due to the action taken on Amazon instead.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [410, 105]}<image>Thought: Type \"ebay.com\" into the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Cars\" to access the category where I can search for \"rayovac triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [283, 225]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_1.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_2.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_3.png"
] | 9,793
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"ebay.com\" into the search bar to navigate to the eBay website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>Thought: Click on \"Cars\" to access the category where I can search for \"rayovac triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [283, 225]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar to focus on it for entering a product query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 283]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_2.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_3.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_4.png"
] | 9,794
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click on \"Cars\" to access the category where I can search for \"rayovac triple a\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [283, 225]}<image>Thought: Click the search bar to focus on it for entering a product query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 283]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"rayovac\" in the search bar to initiate a search for the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"rayovac\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_3.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_4.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_5.png"
] | 9,795
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the search bar to focus on it for entering a product query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [275, 283]}<image>Thought: Type \"rayovac\" in the search bar to initiate a search for the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"rayovac\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the magnifying glass to execute the search for \"rayovac triple a\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 274]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_4.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_5.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_6.png"
] | 9,796
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Type \"rayovac\" in the search bar to initiate a search for the product on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"rayovac\", \"position\": null}<image>Thought: Click the magnifying glass to execute the search for \"rayovac triple a\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 274]}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry labeled \"60 x Rayovac Extra 10 Size Hearing aid batteries\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [301, 665]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_5.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_6.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_7.png"
] | 9,797
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to execute the search for \"rayovac triple a\" on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 274]}<image>Thought: Click the first entry labeled \"60 x Rayovac Extra 10 Size Hearing aid batteries\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [301, 665]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Rayovac AAA batteries listing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_6.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_7.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_8.png"
] | 9,798
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for rayovac triple a on ebay, select the first entry, and add it to the cart.<image>Thought: Click the first entry labeled \"60 x Rayovac Extra 10 Size Hearing aid batteries\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [301, 665]}<image>Thought: Scroll down to view more details about the Rayovac AAA batteries listing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the selected item in your shopping list for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [395, 1110]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/14266394131340524824_7.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_8.png",
"training_data/AITW/aitw_images/webshopping/14266394131340524824_9.png"
] | 9,799
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.