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 \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Type \"target\" in the search bar to find the desired shopping website.\nAction: {\"action\": \"TYPE\", \"value\": \"target\", \"position\": null}<image>Thought: Press enter to initiate the search for \"razer blade\" on the Target website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results and access the \"Target Online - Official Site\" link.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_2.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_3.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_4.png"
] | 11,200
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Press enter to initiate the search for \"razer blade\" on the Target website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results and access the \"Target Online - Official Site\" link.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Online - Official\" to navigate to the Target website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 263]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_3.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_4.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_5.png"
] | 11,201
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results and access the \"Target Online - Official Site\" link.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on \"Online - Official\" to navigate to the Target website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 263]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search\" bar to begin entering the search term \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 277]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_4.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_5.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_6.png"
] | 11,202
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Click on \"Online - Official\" to navigate to the Target website for further browsing.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [200, 263]}<image>Thought: Click the \"Search\" bar to begin entering the search term \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 277]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search bar to initiate a product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_5.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_6.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_7.png"
] | 11,203
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Click the \"Search\" bar to begin entering the search term \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 277]}<image>Thought: Type \"razer blade\" in the search bar to initiate a product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to execute the search for \"razer blade\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_6.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_7.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_8.png"
] | 11,204
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Type \"razer blade\" in the search bar to initiate a product search.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade\", \"position\": null}<image>Thought: Press enter to execute the search for \"razer blade\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the search results for \"razer blade\" that are below the current screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_7.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_8.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_9.png"
] | 11,205
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Press enter to execute the search for \"razer blade\" in the search bar.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the search results for \"razer blade\" that are below the current screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_8.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_9.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_10.png"
] | 11,206
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the search results for \"razer blade\" that are below the current screen.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more results and locate the first entry for selection.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_9.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_10.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_11.png"
] | 11,207
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"razer blade.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more results and locate the first entry for selection.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the blue \"Add to cart\" button to include the selected product in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [286, 461]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_10.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_11.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_12.png"
] | 11,208
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more results and locate the first entry for selection.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the blue \"Add to cart\" button to include the selected product in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [286, 461]}<image>",
"role": "user"
},
{
"content": "Thought: You clicked \"Add to cart\" on the GUI to select the item for purchase. The button indicates you want to store it for later. You likely wish to finalize your shopping by adding this product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [187, 607]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_11.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_12.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_13.png"
] | 11,209
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Search for \"razer blade\" on target, select the first entry, and add it to the cart.<image>Thought: Click the blue \"Add to cart\" button to include the selected product in your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [286, 461]}<image>Thought: You clicked \"Add to cart\" on the GUI to select the item for purchase. The button indicates you want to store it for later. You likely wish to finalize your shopping by adding this product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [187, 607]}<image>",
"role": "user"
},
{
"content": "Thought: The user would confirm the task is complete after successfully adding an item to the cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/7076475261225082519_12.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_13.png",
"training_data/AITW/aitw_images/webshopping/7076475261225082519_14.png"
] | 11,210
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Click CHAT to access customer service for help with the eBay shopping process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 482]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_0.png"
] | 11,211
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click CHAT to access customer service for help with the eBay shopping process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 482]}<image>",
"role": "user"
},
{
"content": "Thought: Status task impossible: You cannot add \"dell xps\" to the cart on eBay because you are on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 37]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_0.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_1.png"
] | 11,212
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click CHAT to access customer service for help with the eBay shopping process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 482]}<image>Thought: Status task impossible: You cannot add \"dell xps\" to the cart on eBay because you are on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 37]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"ebay.com\" in the address bar to navigate to the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_0.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_1.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_2.png"
] | 11,213
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Status task impossible: You cannot add \"dell xps\" to the cart on eBay because you are on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [102, 37]}<image>Thought: Type \"ebay.com\" in the address bar to navigate to the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on eBay.com to access the website for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 85]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_1.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_2.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_3.png"
] | 11,214
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Type \"ebay.com\" in the address bar to navigate to the eBay website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>Thought: Click on eBay.com to access the website for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 85]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Search for anything\" to access the search bar for entering \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 124]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_2.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_3.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_4.png"
] | 11,215
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click on eBay.com to access the website for adding items to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [63, 85]}<image>Thought: Click on \"Search for anything\" to access the search bar for entering \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 124]}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Electronics\" to navigate to the appropriate category for adding \"dell xps\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 125]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_3.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_4.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_5.png"
] | 11,216
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click on \"Search for anything\" to access the search bar for entering \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 124]}<image>Thought: Click on \"Electronics\" to navigate to the appropriate category for adding \"dell xps\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 125]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"dell xps\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_4.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_5.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_6.png"
] | 11,217
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click on \"Electronics\" to navigate to the appropriate category for adding \"dell xps\" to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [52, 125]}<image>Thought: Type \"dell xps\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"dell xps\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 408]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_5.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_6.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_7.png"
] | 11,218
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Type \"dell xps\" in the search bar to find the item.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>Thought: Click on \"dell xps\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 408]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Dell XPS\" listing to view more details about it before adding to cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 464]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_6.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_7.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_8.png"
] | 11,219
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click on \"dell xps\" to view the product details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [16, 408]}<image>Thought: Click on the \"Dell XPS\" listing to view more details about it before adding to cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 464]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the \"Add to cart\" button for the dell xps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_7.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_8.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_9.png"
] | 11,220
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click on the \"Dell XPS\" listing to view more details about it before adding to cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 464]}<image>Thought: Scroll down to find the \"Add to cart\" button for the dell xps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the \"Buy It Now\" button for adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_8.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_9.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_10.png"
] | 11,221
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Scroll down to find the \"Add to cart\" button for the dell xps.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the \"Buy It Now\" button for adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to cart\" to include the item in your shopping cart for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_9.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_10.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_11.png"
] | 11,222
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Scroll down to view the \"Buy It Now\" button for adding the item to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the item in your shopping cart for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"View in cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_10.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_11.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_12.png"
] | 11,223
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click \"Add to cart\" to include the item in your shopping cart for later checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}<image>Thought: Click \"View in cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Go to checkout\" to proceed with the purchase process for the dell xps in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [104, 494]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_11.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_12.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_13.png"
] | 11,224
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"dell xps\" to the cart on ebay, then select checkout.<image>Thought: Click \"View in cart\" to review the items before proceeding to checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [113, 399]}<image>Thought: Click \"Go to checkout\" to proceed with the purchase process for the dell xps in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [104, 494]}<image>",
"role": "user"
},
{
"content": "Thought: Confirm that the task is complete since \"dell xps\" was successfully added to the cart and checkout initiated.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15849611138289969318_12.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_13.png",
"training_data/AITW/aitw_images/webshopping/15849611138289969318_14.png"
] | 11,225
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Click CHAT to seek assistance in locating the USB-A product on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 505]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_0.png"
] | 11,226
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Click CHAT to seek assistance in locating the USB-A product on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 505]}<image>",
"role": "user"
},
{
"content": "Thought: You likely clicked 'X' to dismiss the Walmart Protection Plan prompt after successfully adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 263]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_0.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_1.png"
] | 11,227
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Click CHAT to seek assistance in locating the USB-A product on Walmart.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [164, 505]}<image>Thought: You likely clicked 'X' to dismiss the Walmart Protection Plan prompt after successfully adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 263]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the search bar to initiate the process of adding a usb-a item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 61]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_0.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_1.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_2.png"
] | 11,228
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: You likely clicked 'X' to dismiss the Walmart Protection Plan prompt after successfully adding the item to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 263]}<image>Thought: Click on the search bar to initiate the process of adding a usb-a item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 61]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"usb-a\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_1.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_2.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_3.png"
] | 11,229
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Click on the search bar to initiate the process of adding a usb-a item to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [118, 61]}<image>Thought: Type \"usb-a\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on the usb-a to usb-a cable entry to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 133]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_2.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_3.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_4.png"
] | 11,230
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Type \"usb-a\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-a\", \"position\": null}<image>Thought: Click on the usb-a to usb-a cable entry to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 133]}<image>",
"role": "user"
},
{
"content": "Thought: Click on US8-Cto USB-A to select the item I want to add to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 286]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_3.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_4.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_5.png"
] | 11,231
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Click on the usb-a to usb-a cable entry to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [84, 133]}<image>Thought: Click on US8-Cto USB-A to select the item I want to add to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 286]}<image>",
"role": "user"
},
{
"content": "Thought: Click Add to cart to include the USB-A cable in your shopping selection on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 572]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_4.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_5.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_6.png"
] | 11,232
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add usb-a to the cart on walmart.com<image>Thought: Click on US8-Cto USB-A to select the item I want to add to my cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [192, 286]}<image>Thought: Click Add to cart to include the USB-A cable in your shopping selection on Walmart's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [224, 572]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates the user successfully added a USB-A cable to their cart on Walmart.com. The confirmation \"Added to cart!\" shows that the intended action was completed without issues.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/17009304088465071209_5.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_6.png",
"training_data/AITW/aitw_images/webshopping/17009304088465071209_7.png"
] | 11,233
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Click the Chrome app to access Target's website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1193]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_0.png"
] | 11,234
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the Chrome app to access Target's website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1193]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 740]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_0.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_1.png"
] | 11,235
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the Chrome app to access Target's website for further actions.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1193]}<image>Thought: Click the X to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 740]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove an item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [678, 847]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_0.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_1.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_2.png"
] | 11,236
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the X to remove the item from the cart and clear it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [672, 740]}<image>Thought: Click the X to remove an item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [678, 847]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove an item from the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [674, 857]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_1.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_2.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_3.png"
] | 11,237
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the X to remove an item from the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [678, 847]}<image>Thought: Click the X to remove an item from the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [674, 857]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to remove the current item from the cart before searching for a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [673, 848]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_2.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_3.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_4.png"
] | 11,238
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the X to remove an item from the cart and proceed with clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [674, 857]}<image>Thought: Click the X to remove the current item from the cart before searching for a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [673, 848]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the PERSON icon to access account options and potentially sign in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 401]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_3.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_4.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_5.png"
] | 11,239
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the X to remove the current item from the cart before searching for a new product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [673, 848]}<image>Thought: Click on the PERSON icon to access account options and potentially sign in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 401]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer kraken\" in the search box to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_4.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_5.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_6.png"
] | 11,240
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click on the PERSON icon to access account options and potentially sign in.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [514, 401]}<image>Thought: Type \"razer kraken\" in the search box to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Press enter to submit the search for \"razer kraken\" in the search bar on Target's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_5.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_6.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_7.png"
] | 11,241
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Type \"razer kraken\" in the search box to find the product on Target.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>Thought: Press enter to submit the search for \"razer kraken\" in the search bar on Target's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the first entry, \"Razer Kraken X Gaming,\" to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1291]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_6.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_7.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_8.png"
] | 11,242
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Press enter to submit the search for \"razer kraken\" in the search bar on Target's website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click the first entry, \"Razer Kraken X Gaming,\" to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1291]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for the Razer Kraken on Target's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_7.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_8.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_9.png"
] | 11,243
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Click the first entry, \"Razer Kraken X Gaming,\" to view more details about the product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [508, 1291]}<image>Thought: Scroll down to view more search results for the Razer Kraken on Target's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more details about the Razer Kraken headset and its pricing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_8.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_9.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_10.png"
] | 11,244
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for the Razer Kraken on Target's website.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the Razer Kraken headset and its pricing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to cart\" button to add the selected Razer Kraken item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [491, 1100]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_9.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_10.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_11.png"
] | 11,245
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Clear the cart on target. Search for razer kraken on target, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the Razer Kraken headset and its pricing.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add to cart\" button to add the selected Razer Kraken item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [491, 1100]}<image>",
"role": "user"
},
{
"content": "Thought: The operation indicates that the user was unable to add the Razer Kraken to the cart due to out-of-stock status.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/6896569178964148715_10.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_11.png",
"training_data/AITW/aitw_images/webshopping/6896569178964148715_12.png"
] | 11,246
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>",
"role": "user"
},
{
"content": "Thought: Open the web browser by clicking the Chrome icon to access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [509, 1148]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_0.png"
] | 11,247
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Open the web browser by clicking the Chrome icon to access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [509, 1148]}<image>",
"role": "user"
},
{
"content": "Thought: status task impossible: The user is on Costco's website instead of Best Buy, making it impossible to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 107]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_0.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_1.png"
] | 11,248
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Open the web browser by clicking the Chrome icon to access bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [509, 1148]}<image>Thought: status task impossible: The user is on Costco's website instead of Best Buy, making it impossible to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 107]}<image>",
"role": "user"
},
{
"content": "Thought: Click on Best Buy to access the website and search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 351]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_0.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_1.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_2.png"
] | 11,249
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: status task impossible: The user is on Costco's website instead of Best Buy, making it impossible to view the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 107]}<image>Thought: Click on Best Buy to access the website and search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 351]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART icon to view the items selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [667, 256]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_1.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_2.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_3.png"
] | 11,250
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on Best Buy to access the website and search for the Razer Blade.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 351]}<image>Thought: Click the SHOPPING CART icon to view the items selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [667, 256]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search icon to initiate a search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 272]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_2.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_3.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_4.png"
] | 11,251
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART icon to view the items selected for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [667, 256]}<image>Thought: Click the search icon to initiate a search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 272]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"razer blade\" in the search box to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade \", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_3.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_4.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_5.png"
] | 11,252
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the search icon to initiate a search for \"razer blade.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [358, 272]}<image>Thought: Type \"razer blade\" in the search box to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade \", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"razer blade 14\" to view product details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 286]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_4.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_5.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_6.png"
] | 11,253
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Type \"razer blade\" in the search box to find the desired product on Best Buy.\nAction: {\"action\": \"TYPE\", \"value\": \"razer blade \", \"position\": null}<image>Thought: Click on \"razer blade 14\" to view product details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 286]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the available products resulting from the search for \"razer blade 14\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_5.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_6.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_7.png"
] | 11,254
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click on \"razer blade 14\" to view product details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [112, 286]}<image>Thought: Scroll down to view the available products resulting from the search for \"razer blade 14\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more search results for the razer blade on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_6.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_7.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_8.png"
] | 11,255
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the available products resulting from the search for \"razer blade 14\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for the razer blade on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to see more products listed for \"razer blade 14\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_7.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_8.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_9.png"
] | 11,256
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for the razer blade on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more products listed for \"razer blade 14\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the star to add the selected Razer Blade laptop to favorites for comparison later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 611]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_8.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_9.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_10.png"
] | 11,257
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to see more products listed for \"razer blade 14\" on bestbuy.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the star to add the selected Razer Blade laptop to favorites for comparison later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 611]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view more products since the first entry is not fully visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_9.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_10.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_11.png"
] | 11,258
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the star to add the selected Razer Blade laptop to favorites for comparison later.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [318, 611]}<image>Thought: Scroll down to view more products since the first entry is not fully visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 833]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_10.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_11.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_12.png"
] | 11,259
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more products since the first entry is not fully visible.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 833]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Add to Cart\" button to include the selected Razer Blade laptop in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [586, 838]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_11.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_12.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_13.png"
] | 11,260
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart on bestbuy.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [517, 833]}<image>Thought: Click the \"Add to Cart\" button to include the selected Razer Blade laptop in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [586, 838]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 835]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_12.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_13.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_14.png"
] | 11,261
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click the \"Add to Cart\" button to include the selected Razer Blade laptop in my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [586, 838]}<image>Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 835]}<image>",
"role": "user"
},
{
"content": "Thought: Click \"Add to Cart\" to add the selected Razer Blade laptop to your shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 835]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_13.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_14.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_15.png"
] | 11,262
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: View the shopping cart on bestbuy.com. Search for razer blade on bestbuy.com, select the first entry, and add it to the cart.<image>Thought: Click \"Add to Cart\" to include the selected Razer Blade laptop in your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [564, 835]}<image>Thought: Click \"Add to Cart\" to add the selected Razer Blade laptop to your shopping cart on Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 835]}<image>",
"role": "user"
},
{
"content": "Thought: The user completed their task by adding the Razer Blade to their shopping cart. The GUI confirms that the item was successfully added, indicating they can now proceed with checking out or continue shopping.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/2339058850909279145_14.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_15.png",
"training_data/AITW/aitw_images/webshopping/2339058850909279145_16.png"
] | 11,263
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>",
"role": "user"
},
{
"content": "Thought: Click the Walmart app icon to open the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [484, 1160]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_0.png"
] | 11,264
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the Walmart app icon to open the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [484, 1160]}<image>",
"role": "user"
},
{
"content": "Thought: The user clicked on the eBay sign-in link, likely intending to access their account before modifying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 110]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_0.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_1.png"
] | 11,265
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the Walmart app icon to open the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [484, 1160]}<image>Thought: The user clicked on the eBay sign-in link, likely intending to access their account before modifying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 110]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"walmart.com\" in the search bar to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_0.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_1.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_2.png"
] | 11,266
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: The user clicked on the eBay sign-in link, likely intending to access their account before modifying the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [255, 110]}<image>Thought: Type \"walmart.com\" in the search bar to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click walmart.com to access the website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [195, 240]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_1.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_2.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_3.png"
] | 11,267
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Type \"walmart.com\" in the search bar to access the Walmart website for shopping.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: Click walmart.com to access the website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [195, 240]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll up to navigate to the top of the page where the shopping cart might be accessible.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [650, 195]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_2.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_3.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_4.png"
] | 11,268
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click walmart.com to access the website where I can manage my shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [195, 240]}<image>Thought: Scroll up to navigate to the top of the page where the shopping cart might be accessible.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [650, 195]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to locate and manage the items in the shopping cart on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_3.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_4.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_5.png"
] | 11,269
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Scroll up to navigate to the top of the page where the shopping cart might be accessible.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [650, 195]}<image>Thought: Scroll down to locate and manage the items in the shopping cart on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: You click Remove on the shopping cart item to delete it from your cart. This action directly interacts with the Remove button, allowing you to empty your cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 737]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_4.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_5.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_6.png"
] | 11,270
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Scroll down to locate and manage the items in the shopping cart on walmart.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You click Remove on the shopping cart item to delete it from your cart. This action directly interacts with the Remove button, allowing you to empty your cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 737]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Search Walmart\" bar to begin finding items to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 112]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_5.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_6.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_7.png"
] | 11,271
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: You click Remove on the shopping cart item to delete it from your cart. This action directly interacts with the Remove button, allowing you to empty your cart before adding new items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [99, 737]}<image>Thought: Click the \"Search Walmart\" bar to begin finding items to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 112]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"panasonic triple a\" in the search bar to find the product and add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_6.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_7.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_8.png"
] | 11,272
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the \"Search Walmart\" bar to begin finding items to add to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [346, 112]}<image>Thought: Type \"panasonic triple a\" in the search bar to find the product and add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"panasonic triple a\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 400]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_7.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_8.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_9.png"
] | 11,273
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Type \"panasonic triple a\" in the search bar to find the product and add it to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}<image>Thought: Click on \"panasonic triple a\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 400]}<image>",
"role": "user"
},
{
"content": "Thought: Click the SHOPPING CART to view items ready for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [659, 201]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_8.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_9.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_10.png"
] | 11,274
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click on \"panasonic triple a\" to select the desired product for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [247, 400]}<image>Thought: Click the SHOPPING CART to view items ready for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [659, 201]}<image>",
"role": "user"
},
{
"content": "Thought: You click on \"Search Walmart\" to access the search function for finding products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 203]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_9.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_10.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_11.png"
] | 11,275
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the SHOPPING CART to view items ready for removal.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [659, 201]}<image>Thought: You click on \"Search Walmart\" to access the search function for finding products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 203]}<image>",
"role": "user"
},
{
"content": "Thought: Type \"panasonic triple a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_10.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_11.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_12.png"
] | 11,276
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: You click on \"Search Walmart\" to access the search function for finding products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [379, 203]}<image>Thought: Type \"panasonic triple a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"panasonic triple a batteries\" entry to add the item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [197, 379]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_11.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_12.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_13.png"
] | 11,277
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Type \"panasonic triple a\" in the search bar to find the product for adding to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \" panasonic triple a\", \"position\": null}<image>Thought: Click the \"panasonic triple a batteries\" entry to add the item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [197, 379]}<image>",
"role": "user"
},
{
"content": "Thought: Click the Panasonic triple A option to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [248, 397]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_12.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_13.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_14.png"
] | 11,278
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the \"panasonic triple a batteries\" entry to add the item to your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [197, 379]}<image>Thought: Click the Panasonic triple A option to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [248, 397]}<image>",
"role": "user"
},
{
"content": "Thought: Click the PLUS button to increase the quantity of Panasonic AAA batteries in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [495, 1069]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_13.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_14.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_15.png"
] | 11,279
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Empty the shopping cart on walmart.com. Add panasonic triple a to the cart on walmart.com<image>Thought: Click the Panasonic triple A option to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [248, 397]}<image>Thought: Click the PLUS button to increase the quantity of Panasonic AAA batteries in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [495, 1069]}<image>",
"role": "user"
},
{
"content": "Thought: The task is complete because the user successfully added Panasonic AAA batteries to the shopping cart on Walmart.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/13503537417001105009_14.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_15.png",
"training_data/AITW/aitw_images/webshopping/13503537417001105009_16.png"
] | 11,280
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to find the Amazon Basics AAA product on Newegg.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_0.png"
] | 11,281
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Scroll down to find the Amazon Basics AAA product on Newegg.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click GOOGLE to open the web browser for accessing Newegg.com and searching for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 968]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_0.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_1.png"
] | 11,282
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Scroll down to find the Amazon Basics AAA product on Newegg.com.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click GOOGLE to open the web browser for accessing Newegg.com and searching for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 968]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the Google icon to open the browser and search for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 955]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_0.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_1.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_2.png"
] | 11,283
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click GOOGLE to open the web browser for accessing Newegg.com and searching for Amazon Basics AAA batteries.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [123, 968]}<image>Thought: Click on the Google icon to open the browser and search for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 955]}<image>",
"role": "user"
},
{
"content": "Thought: Click the link for Target to access their website and continue shopping for the product you need.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 172]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_1.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_2.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_3.png"
] | 11,284
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click on the Google icon to open the browser and search for Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [110, 955]}<image>Thought: Click the link for Target to access their website and continue shopping for the product you need.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 172]}<image>",
"role": "user"
},
{
"content": "Thought: Click the X to close the search bar and return to the previous screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [652, 99]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_2.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_3.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_4.png"
] | 11,285
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click the link for Target to access their website and continue shopping for the product you need.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [168, 172]}<image>Thought: Click the X to close the search bar and return to the previous screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [652, 99]}<image>",
"role": "user"
},
{
"content": "Thought: You want to access Newegg's website by typing its URL in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_3.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_4.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_5.png"
] | 11,286
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click the X to close the search bar and return to the previous screen.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [652, 99]}<image>Thought: You want to access Newegg's website by typing its URL in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"Computer Parts, La...ore - Newegg.com\" to access the Newegg website for further product search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 195]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_4.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_5.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_6.png"
] | 11,287
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: You want to access Newegg's website by typing its URL in the search bar.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Click on \"Computer Parts, La...ore - Newegg.com\" to access the Newegg website for further product search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 195]}<image>",
"role": "user"
},
{
"content": "Thought: Click OK to dismiss the notification and proceed with accessing newegg.com for the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [596, 795]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_5.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_6.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_7.png"
] | 11,288
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click on \"Computer Parts, La...ore - Newegg.com\" to access the Newegg website for further product search.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [178, 195]}<image>Thought: Click OK to dismiss the notification and proceed with accessing newegg.com for the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [596, 795]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the \"Computer Parts, La...ore - Newegg.com\" link to navigate to the desired section of the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 188]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_6.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_7.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_8.png"
] | 11,289
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click OK to dismiss the notification and proceed with accessing newegg.com for the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [596, 795]}<image>Thought: Click on the \"Computer Parts, La...ore - Newegg.com\" link to navigate to the desired section of the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 188]}<image>",
"role": "user"
},
{
"content": "Thought: Click the search bar labeled \"Keywords: Model #, Item #\" to enter the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 239]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_7.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_8.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_9.png"
] | 11,290
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click on the \"Computer Parts, La...ore - Newegg.com\" link to navigate to the desired section of the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [261, 188]}<image>Thought: Click the search bar labeled \"Keywords: Model #, Item #\" to enter the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 239]}<image>",
"role": "user"
},
{
"content": "Thought: Type in the search bar to find \"amazon basics triple a\" product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_8.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_9.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_10.png"
] | 11,291
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click the search bar labeled \"Keywords: Model #, Item #\" to enter the item details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [181, 239]}<image>Thought: Type in the search bar to find \"amazon basics triple a\" product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click on \"amazon basics triple a\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 236]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_9.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_10.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_11.png"
] | 11,292
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Type in the search bar to find \"amazon basics triple a\" product on Newegg.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon basics triple a\", \"position\": null}<image>Thought: Click on \"amazon basics triple a\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 236]}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"Wireless Charging\" option to view more details about the Amazon Basics Triple A product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 1021]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_10.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_11.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_12.png"
] | 11,293
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click on \"amazon basics triple a\" to view product details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 236]}<image>Thought: Click the \"Wireless Charging\" option to view more details about the Amazon Basics Triple A product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 1021]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the product link to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [657, 610]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_11.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_12.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_13.png"
] | 11,294
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click the \"Wireless Charging\" option to view more details about the Amazon Basics Triple A product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [130, 1021]}<image>Thought: Click on the product link to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [657, 610]}<image>",
"role": "user"
},
{
"content": "Thought: You click on \"Basics\" to select the desired Amazon Basics product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 1005]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_12.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_13.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_14.png"
] | 11,295
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click on the product link to view its details and add it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [657, 610]}<image>Thought: You click on \"Basics\" to select the desired Amazon Basics product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 1005]}<image>",
"role": "user"
},
{
"content": "Thought: Scroll down to view the \"ADD TO CART\" option for the Amazon Basics item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_13.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_14.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_15.png"
] | 11,296
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: You click on \"Basics\" to select the desired Amazon Basics product from the search results.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [163, 1005]}<image>Thought: Scroll down to view the \"ADD TO CART\" option for the Amazon Basics item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>",
"role": "user"
},
{
"content": "Thought: Click the \"ADD TO CART\" button to select the item for purchase on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [338, 1391]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_14.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_15.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_16.png"
] | 11,297
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Scroll down to view the \"ADD TO CART\" option for the Amazon Basics item.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"ADD TO CART\" button to select the item for purchase on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [338, 1391]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the SHOPPING CART icon to view items added to cart and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 1392]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_15.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_16.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_17.png"
] | 11,298
|
[
{
"content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add amazon basics triple a to the cart on newegg.com, then select checkout.<image>Thought: Click the \"ADD TO CART\" button to select the item for purchase on Newegg.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [338, 1391]}<image>Thought: Click on the SHOPPING CART icon to view items added to cart and proceed with checkout.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [50, 1392]}<image>",
"role": "user"
},
{
"content": "Thought: Click on the 'SECURE CHECKOUT' button to proceed with the checkout process after adding items to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [282, 1325]}",
"role": "assistant"
}
] |
[
"training_data/AITW/aitw_images/webshopping/15940715892858092774_16.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_17.png",
"training_data/AITW/aitw_images/webshopping/15940715892858092774_18.png"
] | 11,299
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.