messages
listlengths
2
200
images
listlengths
1
3
custom_id
int64
0
66.2k
[ { "content": "You are an assistant trained to navigate the mobile phone. \nGiven a task instruction, a screen observation, and an action history sequence, \noutput the next action and wait for the next observation. \nHere is the action space:\n1. `CLICK`: Click on an element, value is not applicable and the position [x,y] is required. \n2. `TYPE`: Type a string into an element, value is a string to type and the position is not applicable.\n3. `SELECT`: Select a value for an element, value is the value to select and the position is not applicable.\n4. `SCROLL UP`: Scroll up for the screen.\n5. `SCROLL DOWN`: Scroll down for the screen.\n6. `SCROLL LEFT`: Scroll left for the screen.\n7. `SCROLL RIGHT`: Scroll right for the screen.\n8. `PRESS BACK`: Press for returning to the previous step, value and position are not applicable.\n9. `PRESS HOME`: Press for returning to the home screen, value and position are not applicable.\n10. `PRESS ENTER`: Press for submitting the input content, value and position are not applicable.\n11. `STATUS TASK COMPLETE`: Indicate the task is completed, value and position are not applicable.\n12. `STATUS TASK IMPOSSIBLE `: Indicate the task is impossible to complete, value and position are not applicable.\n\nFormat your response as\nThought: <your reasoning process>\nAction: <the next action>\n\nFormat the action as a JSON object with the following keys:\n{\"action\": \"ACTION_TYPE\", \"value\": \"element\", \"position\": [x,y]}\n\nIf value or position is not applicable, set it as `None`.\nPosition represents the absolute pixel coordinates on the screenshot.\nTask: Add \"razer naga\" to the cart on amazon<image>Thought: Type \"razer naga\" in the search bar to find the specific product I want to add to the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga \", \"position\": null}<image>Thought: Click the magnifying glass to initiate a product search for \"razer naga.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [656, 279]}<image>", "role": "user" }, { "content": "Thought: Click the \"Razer Naga X Wired MMO Gaming Mouse\" to select it for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 622]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14824113175601358458_2.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_3.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_4.png" ]
7,200
[ { "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: Add \"razer naga\" to the cart on amazon<image>Thought: Click the magnifying glass to initiate a product search for \"razer naga.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [656, 279]}<image>Thought: Click the \"Razer Naga X Wired MMO Gaming Mouse\" to select it for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 622]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more product details and options for the Razer Naga mouse.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14824113175601358458_3.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_4.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_5.png" ]
7,201
[ { "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: Add \"razer naga\" to the cart on amazon<image>Thought: Click the \"Razer Naga X Wired MMO Gaming Mouse\" to select it for adding to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [454, 622]}<image>Thought: Scroll down to view more product details and options for the Razer Naga mouse.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more options for the \"razer naga\" mouse available for purchase on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14824113175601358458_4.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_5.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_6.png" ]
7,202
[ { "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: Add \"razer naga\" to the cart on amazon<image>Thought: Scroll down to view more product details and options for the Razer Naga mouse.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more options for the \"razer naga\" mouse available for purchase on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click \"Add to Cart\" to confirm the selection of the Razer Naga.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 1244]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14824113175601358458_5.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_6.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_7.png" ]
7,203
[ { "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: Add \"razer naga\" to the cart on amazon<image>Thought: Scroll down to view more options for the \"razer naga\" mouse available for purchase on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to Cart\" to confirm the selection of the Razer Naga.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [418, 1244]}<image>", "role": "user" }, { "content": "Thought: You successfully added \"razer naga\" to your cart, reflected by the subtotal update and item list.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14824113175601358458_6.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_7.png", "training_data/AITW/aitw_images/webshopping/14824113175601358458_8.png" ]
7,204
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>", "role": "user" }, { "content": "Thought: Press home to exit the current email setup and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_0.png" ]
7,205
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current email setup and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on the browser icon to open it and access Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 895]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_0.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_1.png" ]
7,206
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current email setup and return to the main screen for further actions.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the browser icon to open it and access Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 895]}<image>", "role": "user" }, { "content": "Thought: Since the shopping cart indicated an item, click on the cart icon to access the contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 80]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_0.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_1.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_2.png" ]
7,207
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the browser icon to open it and access Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [383, 895]}<image>Thought: Since the shopping cart indicated an item, click on the cart icon to access the contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 80]}<image>", "role": "user" }, { "content": "Thought: Type \"walmart\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_1.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_2.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_3.png" ]
7,208
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Since the shopping cart indicated an item, click on the cart icon to access the contents.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [212, 80]}<image>Thought: Type \"walmart\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the link for walmart.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 168]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_2.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_3.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_4.png" ]
7,209
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"walmart\" in the search bar to navigate to Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart\", \"position\": null}<image>Thought: Click the link for walmart.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 168]}<image>", "role": "user" }, { "content": "Thought: Click the SHOPPING CART to review current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 140]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_3.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_4.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_5.png" ]
7,210
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the link for walmart.com to access the website and start shopping.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 168]}<image>Thought: Click the SHOPPING CART to review current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 140]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more items in the cart and determine which ones should be cleared.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_4.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_5.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_6.png" ]
7,211
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART to review current items before clearing it.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [490, 140]}<image>Thought: Scroll down to view more items in the cart and determine which ones should be cleared.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on the item entry to select it and view more details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 414]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_5.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_6.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_7.png" ]
7,212
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more items in the cart and determine which ones should be cleared.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the item entry to select it and view more details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 414]}<image>", "role": "user" }, { "content": "Thought: Click \"Remove\" to delete the selected item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 438]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_6.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_7.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_8.png" ]
7,213
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the item entry to select it and view more details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [361, 414]}<image>Thought: Click \"Remove\" to delete the selected item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 438]}<image>", "role": "user" }, { "content": "Thought: Click the \"Search Walmart\" bar to begin searching for items in the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [273, 97]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_7.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_8.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_9.png" ]
7,214
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click \"Remove\" to delete the selected item from the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [78, 438]}<image>Thought: Click the \"Search Walmart\" bar to begin searching for items in the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [273, 97]}<image>", "role": "user" }, { "content": "Thought: Type \"razer naga\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_8.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_9.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_10.png" ]
7,215
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the \"Search Walmart\" bar to begin searching for items in the shopping platform.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [273, 97]}<image>Thought: Type \"razer naga\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Press enter to submit the search query for \"razer naga\" in the search bar on Walmart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_9.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_10.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_11.png" ]
7,216
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"razer naga\" in the search bar to find the product on Walmart's website.\nAction: {\"action\": \"TYPE\", \"value\": \"razer naga\", \"position\": null}<image>Thought: Press enter to submit the search query for \"razer naga\" in the search bar on Walmart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more results for \"razer naga\" and find the desired item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_10.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_11.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_12.png" ]
7,217
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Press enter to submit the search query for \"razer naga\" in the search bar on Walmart.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more results for \"razer naga\" and find the desired item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on the \"+ Add\" button to place the selected item in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 809]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_11.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_12.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_13.png" ]
7,218
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more results for \"razer naga\" and find the desired item to add to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click on the \"+ Add\" button to place the selected item in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 809]}<image>", "role": "user" }, { "content": "Thought: Click the price tag to review the item details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 93]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_12.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_13.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_14.png" ]
7,219
[ { "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: Clear the shopping cart on walmart. Search for \"razer naga\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on the \"+ Add\" button to place the selected item in the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [387, 809]}<image>Thought: Click the price tag to review the item details before adding it to the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 93]}<image>", "role": "user" }, { "content": "Thought: You have successfully added the \"Razer Naga\" item to your cart, fulfilling your shopping task.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/9533816293746786364_13.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_14.png", "training_data/AITW/aitw_images/webshopping/9533816293746786364_15.png" ]
7,220
[ { "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: Clear the cart on newegg.<image>", "role": "user" }, { "content": "Thought: Status task impossible; the current screen displays contacts, not the Newegg cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_0.png" ]
7,221
[ { "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: Clear the cart on newegg.<image>Thought: Status task impossible; the current screen displays contacts, not the Newegg cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the Chrome app icon to open the browser and navigate to Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_0.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_1.png" ]
7,222
[ { "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: Clear the cart on newegg.<image>Thought: Status task impossible; the current screen displays contacts, not the Newegg cart.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome app icon to open the browser and navigate to Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}<image>", "role": "user" }, { "content": "Thought: You click on \"or its affiliates\" to find more information related to your task on Amazon's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_0.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_1.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_2.png" ]
7,223
[ { "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: Clear the cart on newegg.<image>Thought: Click the Chrome app icon to open the browser and navigate to Newegg.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}<image>Thought: You click on \"or its affiliates\" to find more information related to your task on Amazon's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}<image>", "role": "user" }, { "content": "Thought: Click on the URL to navigate to the Amazon sign-in page for account access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 95]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_1.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_2.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_3.png" ]
7,224
[ { "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: Clear the cart on newegg.<image>Thought: You click on \"or its affiliates\" to find more information related to your task on Amazon's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [369, 906]}<image>Thought: Click on the URL to navigate to the Amazon sign-in page for account access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 95]}<image>", "role": "user" }, { "content": "Thought: Type \"newegg.com\" in the search bar to navigate to Newegg's website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_2.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_3.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_4.png" ]
7,225
[ { "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: Clear the cart on newegg.<image>Thought: Click on the URL to navigate to the Amazon sign-in page for account access.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [262, 95]}<image>Thought: Type \"newegg.com\" in the search bar to navigate to Newegg's website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on \"newegg.com\" to navigate to the Newegg homepage for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 250]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_3.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_4.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_5.png" ]
7,226
[ { "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: Clear the cart on newegg.<image>Thought: Type \"newegg.com\" in the search bar to navigate to Newegg's website for clearing the cart.\nAction: {\"action\": \"TYPE\", \"value\": \"newegg.com\", \"position\": null}<image>Thought: Click on \"newegg.com\" to navigate to the Newegg homepage for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 250]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more options and locate the cart section on newegg.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_4.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_5.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_6.png" ]
7,227
[ { "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: Clear the cart on newegg.<image>Thought: Click on \"newegg.com\" to navigate to the Newegg homepage for cart management.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [139, 250]}<image>Thought: Scroll down to view more options and locate the cart section on newegg.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the Newegg.com link to access the website where the cart can be managed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 787]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_5.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_6.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_7.png" ]
7,228
[ { "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: Clear the cart on newegg.<image>Thought: Scroll down to view more options and locate the cart section on newegg.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the Newegg.com link to access the website where the cart can be managed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 787]}<image>", "role": "user" }, { "content": "Thought: Click on the SHOPPING CART icon to access the contents of your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [427, 115]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_6.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_7.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_8.png" ]
7,229
[ { "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: Clear the cart on newegg.<image>Thought: Click the Newegg.com link to access the website where the cart can be managed.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [94, 787]}<image>Thought: Click on the SHOPPING CART icon to access the contents of your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [427, 115]}<image>", "role": "user" }, { "content": "Thought: Clearing the cart is complete as indicated by the \"Cart Empty\" message.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/16964093935991548926_7.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_8.png", "training_data/AITW/aitw_images/webshopping/16964093935991548926_9.png" ]
7,230
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>", "role": "user" }, { "content": "Thought: Open the Costco app or website by clicking on the relevant icon to access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 838]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_0.png" ]
7,231
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Open the Costco app or website by clicking on the relevant icon to access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 838]}<image>", "role": "user" }, { "content": "Thought: Click on the target.com/cart to access the shopping cart interface on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [309, 79]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_0.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_1.png" ]
7,232
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Open the Costco app or website by clicking on the relevant icon to access your shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [372, 838]}<image>Thought: Click on the target.com/cart to access the shopping cart interface on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [309, 79]}<image>", "role": "user" }, { "content": "Thought: Type \"costco\" in the search bar to navigate to the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \" costco\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_0.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_1.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_2.png" ]
7,233
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Click on the target.com/cart to access the shopping cart interface on Target's website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [309, 79]}<image>Thought: Type \"costco\" in the search bar to navigate to the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \" costco\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Press enter to search for \"costco\" and access the Costco website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_1.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_2.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_3.png" ]
7,234
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Type \"costco\" in the search bar to navigate to the Costco website.\nAction: {\"action\": \"TYPE\", \"value\": \" costco\", \"position\": null}<image>Thought: Press enter to search for \"costco\" and access the Costco website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click Search to access the search function and find the Acer Predator product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 221]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_2.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_3.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_4.png" ]
7,235
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Press enter to search for \"costco\" and access the Costco website.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Click Search to access the search function and find the Acer Predator product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 221]}<image>", "role": "user" }, { "content": "Thought: Type \"acer predator\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_3.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_4.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_5.png" ]
7,236
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Click Search to access the search function and find the Acer Predator product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [226, 221]}<image>Thought: Type \"acer predator\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Type \"Acer Predator\" into the search bar to find the product. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_4.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_5.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_6.png" ]
7,237
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Type \"acer predator\" in the search bar to find the product.\nAction: {\"action\": \"TYPE\", \"value\": \"acer predator\", \"position\": null}<image>Thought: Type \"Acer Predator\" into the search bar to find the product. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view search results for \"acer predator\" and find the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_5.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_6.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_7.png" ]
7,238
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Type \"Acer Predator\" into the search bar to find the product. Press enter to execute the search and view results.\nAction: {\"action\": \"PRESS ENTER\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view search results for \"acer predator\" and find the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the \"Add\" button to place the Acer Predator into the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 812]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_6.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_7.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_8.png" ]
7,239
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Scroll down to view search results for \"acer predator\" and find the option to add it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click the \"Add\" button to place the Acer Predator into the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 812]}<image>", "role": "user" }, { "content": "Thought: Scroll up to view the Acer Predator options available on the Costco shopping page.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_7.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_8.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_9.png" ]
7,240
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Click the \"Add\" button to place the Acer Predator into the shopping cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [438, 812]}<image>Thought: Scroll up to view the Acer Predator options available on the Costco shopping page.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the SHOPPING CART to access and manage the current items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 147]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_8.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_9.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_10.png" ]
7,241
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Scroll up to view the Acer Predator options available on the Costco shopping page.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click the SHOPPING CART to access and manage the current items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 147]}<image>", "role": "user" }, { "content": "Thought: Click Checkout to proceed with the purchase of the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [288, 970]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_9.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_10.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_11.png" ]
7,242
[ { "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: Empty the shopping cart on costco. Add acer predator to the cart on costco<image>Thought: Click the SHOPPING CART to access and manage the current items in your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [498, 147]}<image>Thought: Click Checkout to proceed with the purchase of the items currently in the cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [288, 970]}<image>", "role": "user" }, { "content": "Thought: Status task complete indicates that you successfully emptied the shopping cart and added the Acer Predator to it.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/6987002433789770736_10.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_11.png", "training_data/AITW/aitw_images/webshopping/6987002433789770736_12.png" ]
7,243
[ { "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: Search for the best rated 4k tvs on Walmart.<image>", "role": "user" }, { "content": "Thought: Scroll down to view more options in the Walmart app after initiating a search.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_0.png" ]
7,244
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: Scroll down to view more options in the Walmart app after initiating a search.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: You want to use Google to search for the best rated 4k TVs on Walmart. Clicking Google opens the search engine interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 336]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_0.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_1.png" ]
7,245
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: Scroll down to view more options in the Walmart app after initiating a search.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: You want to use Google to search for the best rated 4k TVs on Walmart. Clicking Google opens the search engine interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 336]}<image>", "role": "user" }, { "content": "Thought: Click on the link to access crate & barrel's website and continue searching for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 76]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_0.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_1.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_2.png" ]
7,246
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: You want to use Google to search for the best rated 4k TVs on Walmart. Clicking Google opens the search engine interface.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [49, 336]}<image>Thought: Click on the link to access crate & barrel's website and continue searching for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 76]}<image>", "role": "user" }, { "content": "Thought: Click X to close the current search, as it’s not relevant to finding 4K TVs on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 31]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_1.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_2.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_3.png" ]
7,247
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: Click on the link to access crate & barrel's website and continue searching for items.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [194, 76]}<image>Thought: Click X to close the current search, as it’s not relevant to finding 4K TVs on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 31]}<image>", "role": "user" }, { "content": "Thought: Type \"4k tvs on Walmart\" in the search bar to find relevant listings.\nAction: {\"action\": \"TYPE\", \"value\": \"4k tvs on Walmart.\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_2.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_3.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_4.png" ]
7,248
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: Click X to close the current search, as it’s not relevant to finding 4K TVs on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [245, 31]}<image>Thought: Type \"4k tvs on Walmart\" in the search bar to find relevant listings.\nAction: {\"action\": \"TYPE\", \"value\": \"4k tvs on Walmart.\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on \"4k tvs walmart\" to directly access Walmart's selection of 4k televisions for better ratings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 77]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_3.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_4.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_5.png" ]
7,249
[ { "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: Search for the best rated 4k tvs on Walmart.<image>Thought: Type \"4k tvs on Walmart\" in the search bar to find relevant listings.\nAction: {\"action\": \"TYPE\", \"value\": \"4k tvs on Walmart.\", \"position\": null}<image>Thought: Click on \"4k tvs walmart\" to directly access Walmart's selection of 4k televisions for better ratings.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [68, 77]}<image>", "role": "user" }, { "content": "Thought: You have successfully located and reviewed the search results for \"4k tvs walmart\" on Google.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/5919104303918679645_4.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_5.png", "training_data/AITW/aitw_images/webshopping/5919104303918679645_6.png" ]
7,250
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>", "role": "user" }, { "content": "Thought: Press home to exit the current app and return to the main screen for easier access to eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_0.png" ]
7,251
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and return to the main screen for easier access to eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the eBay app icon to open it and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1211]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_0.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_1.png" ]
7,252
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current app and return to the main screen for easier access to eBay.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the eBay app icon to open it and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1211]}<image>", "role": "user" }, { "content": "Thought: Recognize that you are currently on Amazon's cart page instead of eBay. Click the URL to access the correct website for eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 106]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_0.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_1.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_2.png" ]
7,253
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click the eBay app icon to open it and proceed with the task.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [505, 1211]}<image>Thought: Recognize that you are currently on Amazon's cart page instead of eBay. Click the URL to access the correct website for eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 106]}<image>", "role": "user" }, { "content": "Thought: Type \"ebay.com\" in the search box to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_1.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_2.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_3.png" ]
7,254
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Recognize that you are currently on Amazon's cart page instead of eBay. Click the URL to access the correct website for eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [289, 106]}<image>Thought: Type \"ebay.com\" in the search box to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on ebay.com to navigate to the eBay website where I can search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 239]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_2.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_3.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_4.png" ]
7,255
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Type \"ebay.com\" in the search box to navigate to eBay's website.\nAction: {\"action\": \"TYPE\", \"value\": \"ebay.com\", \"position\": null}<image>Thought: Click on ebay.com to navigate to the eBay website where I can search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 239]}<image>", "role": "user" }, { "content": "Thought: Click the SHOPPING CART to access your current items and clear them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [584, 207]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_3.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_4.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_5.png" ]
7,256
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click on ebay.com to navigate to the eBay website where I can search for products.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [179, 239]}<image>Thought: Click the SHOPPING CART to access your current items and clear them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [584, 207]}<image>", "role": "user" }, { "content": "Thought: Click the magnifying glass to begin a search for Razer Kraken on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 201]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_4.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_5.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_6.png" ]
7,257
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click the SHOPPING CART to access your current items and clear them.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [584, 207]}<image>Thought: Click the magnifying glass to begin a search for Razer Kraken on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 201]}<image>", "role": "user" }, { "content": "Thought: Type \"razer kraken\" in the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_5.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_6.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_7.png" ]
7,258
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to begin a search for Razer Kraken on eBay.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [384, 201]}<image>Thought: Type \"razer kraken\" in the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the magnifying glass to initiate the search for \"razer kraken\" on eBay.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 298]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_6.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_7.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_8.png" ]
7,259
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Type \"razer kraken\" in the search bar to initiate a product search on eBay.\nAction: {\"action\": \"TYPE\", \"value\": \"razer kraken\", \"position\": null}<image>Thought: Click the magnifying glass to initiate the search for \"razer kraken\" on eBay.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 298]}<image>", "role": "user" }, { "content": "Thought: Click on \"Gaming Headset\" to view the details and options for the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 774]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_7.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_8.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_9.png" ]
7,260
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to initiate the search for \"razer kraken\" on eBay.com.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [649, 298]}<image>Thought: Click on \"Gaming Headset\" to view the details and options for the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 774]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more details of the Razer Kraken headset on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_8.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_9.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_10.png" ]
7,261
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Click on \"Gaming Headset\" to view the details and options for the desired product.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [373, 774]}<image>Thought: Scroll down to view more details of the Razer Kraken headset on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click \"Add to cart\" to include the selected Razer Kraken headset in the shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [392, 1208]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_9.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_10.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_11.png" ]
7,262
[ { "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: Clear the cart on ebay.com. Search for razer kraken on ebay.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details of the Razer Kraken headset on eBay.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add to cart\" to include the selected Razer Kraken headset in the shopping cart for future purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [392, 1208]}<image>", "role": "user" }, { "content": "Thought: You have successfully completed the task of adding the Razer Kraken to your cart on ebay.com.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/14943088806578486285_10.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_11.png", "training_data/AITW/aitw_images/webshopping/14943088806578486285_12.png" ]
7,263
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>", "role": "user" }, { "content": "Thought: Press home to exit the current screen and return to the main menu for accessing a web browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_0.png" ]
7,264
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current screen and return to the main menu for accessing a web browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: You clicked on the CHAT icon instead of the Amazon app, indicating a mistake in your task execution process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [116, 539]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_0.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_1.png" ]
7,265
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current screen and return to the main menu for accessing a web browser.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: You clicked on the CHAT icon instead of the Amazon app, indicating a mistake in your task execution process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [116, 539]}<image>", "role": "user" }, { "content": "Thought: Type \"amazon\" in the search bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_0.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_1.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_2.png" ]
7,266
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: You clicked on the CHAT icon instead of the Amazon app, indicating a mistake in your task execution process.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [116, 539]}<image>Thought: Type \"amazon\" in the search bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on the Amazon link to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 68]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_1.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_2.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_3.png" ]
7,267
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type \"amazon\" in the search bar to navigate to the Amazon website.\nAction: {\"action\": \"TYPE\", \"value\": \"amazon\", \"position\": null}<image>Thought: Click on the Amazon link to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 68]}<image>", "role": "user" }, { "content": "Thought: Click the Amazon.com link to access the online shopping site for viewing your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 156]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_2.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_3.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_4.png" ]
7,268
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click on the Amazon link to access the website.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [65, 68]}<image>Thought: Click the Amazon.com link to access the online shopping site for viewing your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 156]}<image>", "role": "user" }, { "content": "Thought: Click the search bar at the top of the Amazon homepage to input your search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 98]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_3.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_4.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_5.png" ]
7,269
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the Amazon.com link to access the online shopping site for viewing your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [42, 156]}<image>Thought: Click the search bar at the top of the Amazon homepage to input your search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 98]}<image>", "role": "user" }, { "content": "Thought: Type \"dell xps\" in the search bar to find the desired product on Amazon's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_4.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_5.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_6.png" ]
7,270
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the search bar at the top of the Amazon homepage to input your search query.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [73, 98]}<image>Thought: Type \"dell xps\" in the search bar to find the desired product on Amazon's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the magnifying glass to execute the search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 96]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_5.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_6.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_7.png" ]
7,271
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Type \"dell xps\" in the search bar to find the desired product on Amazon's website.\nAction: {\"action\": \"TYPE\", \"value\": \"dell xps\", \"position\": null}<image>Thought: Click the magnifying glass to execute the search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 96]}<image>", "role": "user" }, { "content": "Thought: Click on the first entry that appears in the search results for \"dell xps\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 251]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_6.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_7.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_8.png" ]
7,272
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click the magnifying glass to execute the search for \"dell xps.\"\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [244, 96]}<image>Thought: Click on the first entry that appears in the search results for \"dell xps\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 251]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more details about the Dell XPS product listed on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_7.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_8.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_9.png" ]
7,273
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Click on the first entry that appears in the search results for \"dell xps\" to view its details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [143, 251]}<image>Thought: Scroll down to view more details about the Dell XPS product listed on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click Add to Cart to add the selected Dell XPS item to your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 497]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_8.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_9.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_10.png" ]
7,274
[ { "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: View the shopping cart on amazon.com. Search for \"dell xps\" on amazon.com, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the Dell XPS product listed on Amazon.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click Add to Cart to add the selected Dell XPS item to your shopping cart for purchase.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [133, 497]}<image>", "role": "user" }, { "content": "Thought: You have successfully viewed the shopping cart on amazon.com, confirming the addition of your selected items.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1408243745991097544_9.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_10.png", "training_data/AITW/aitw_images/webshopping/1408243745991097544_11.png" ]
7,275
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>", "role": "user" }, { "content": "Thought: Press home to exit the current application and return to the main screen to start a new task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_0.png" ]
7,276
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current application and return to the main screen to start a new task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click the Chrome icon to open the browser for searching \"usb-b\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 893]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_0.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_1.png" ]
7,277
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Press home to exit the current application and return to the main screen to start a new task.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click the Chrome icon to open the browser for searching \"usb-b\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 893]}<image>", "role": "user" }, { "content": "Thought: You need to sign into your Target account to access the cart, indicated by the blue spot on target.com/cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 83]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_0.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_1.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_2.png" ]
7,278
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click the Chrome icon to open the browser for searching \"usb-b\" on Walmart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 893]}<image>Thought: You need to sign into your Target account to access the cart, indicated by the blue spot on target.com/cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 83]}<image>", "role": "user" }, { "content": "Thought: Type \"walmart.com\" to navigate to Walmart's website for searching products.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_1.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_2.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_3.png" ]
7,279
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: You need to sign into your Target account to access the cart, indicated by the blue spot on target.com/cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 83]}<image>Thought: Type \"walmart.com\" to navigate to Walmart's website for searching products.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: You would click on \"walmart.com\" to navigate to the website and start your search for \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 177]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_2.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_3.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_4.png" ]
7,280
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"walmart.com\" to navigate to Walmart's website for searching products.\nAction: {\"action\": \"TYPE\", \"value\": \"walmart.com\", \"position\": null}<image>Thought: You would click on \"walmart.com\" to navigate to the website and start your search for \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 177]}<image>", "role": "user" }, { "content": "Thought: Click on \"Search everything at V\" to access the search bar for entering \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 167]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_3.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_4.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_5.png" ]
7,281
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: You would click on \"walmart.com\" to navigate to the website and start your search for \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [158, 177]}<image>Thought: Click on \"Search everything at V\" to access the search bar for entering \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 167]}<image>", "role": "user" }, { "content": "Thought: Type \"usb-b\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-b\", \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_4.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_5.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_6.png" ]
7,282
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on \"Search everything at V\" to access the search bar for entering \"usb-b\".\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [215, 167]}<image>Thought: Type \"usb-b\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-b\", \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on \"usb-b\" to select the first search result from the suggestions and view details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 253]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_5.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_6.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_7.png" ]
7,283
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Type \"usb-b\" in the search bar to find the product on Walmart.\nAction: {\"action\": \"TYPE\", \"value\": \"usb-b\", \"position\": null}<image>Thought: Click on \"usb-b\" to select the first search result from the suggestions and view details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 253]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more search results for \"usb-b\" on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_6.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_7.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_8.png" ]
7,284
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on \"usb-b\" to select the first search result from the suggestions and view details.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [64, 253]}<image>Thought: Scroll down to view more search results for \"usb-b\" on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll up to view more search results for \"usb-b\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_7.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_8.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_9.png" ]
7,285
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"usb-b\" on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view more search results for \"usb-b\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to see more search results for \"usb-b\" and find the first entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_8.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_9.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_10.png" ]
7,286
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll up to view more search results for \"usb-b\" and locate the first entry.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Scroll down to see more search results for \"usb-b\" and find the first entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more search results for \"usb-b\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_9.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_10.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_11.png" ]
7,287
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to see more search results for \"usb-b\" and find the first entry.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more search results for \"usb-b\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll up to view the first entry for \"usb-b\" that likely needs selection.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_10.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_11.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_12.png" ]
7,288
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more search results for \"usb-b\".\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll up to view the first entry for \"usb-b\" that likely needs selection.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on \"Braided\" to filter search results for a specific type of USB cable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 342]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_11.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_12.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_13.png" ]
7,289
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll up to view the first entry for \"usb-b\" that likely needs selection.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>Thought: Click on \"Braided\" to filter search results for a specific type of USB cable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 342]}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more product details and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_12.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_13.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_14.png" ]
7,290
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Click on \"Braided\" to filter search results for a specific type of USB cable.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [206, 342]}<image>Thought: Scroll down to view more product details and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_13.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_14.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_15.png" ]
7,291
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more product details and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view more details about the selected item on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_14.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_15.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_16.png" ]
7,292
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more product details and ensure it's the correct item before adding it to the cart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view more details about the selected item on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll down to view the product options and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_15.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_16.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_17.png" ]
7,293
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view more details about the selected item on Walmart.\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Scroll down to view the product options and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click \"Add\" on the selected item to add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [421, 1035]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_16.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_17.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_18.png" ]
7,294
[ { "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: Search for \"usb-b\" on walmart, select the first entry, and add it to the cart.<image>Thought: Scroll down to view the product options and find the first entry for \"usb-b.\"\nAction: {\"action\": \"SCROLL DOWN\", \"value\": null, \"position\": null}<image>Thought: Click \"Add\" on the selected item to add it to your cart.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [421, 1035]}<image>", "role": "user" }, { "content": "Thought: You completed the task by successfully adding the \"usb-b\" item from Walmart to your cart.\nAction: {\"action\": \"STATUS TASK COMPLETE\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/1986854220218543300_17.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_18.png", "training_data/AITW/aitw_images/webshopping/1986854220218543300_19.png" ]
7,295
[ { "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 usb-b to the cart on bestbuy, then select checkout.<image>", "role": "user" }, { "content": "Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/4806571780686350312_0.png" ]
7,296
[ { "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 usb-b to the cart on bestbuy, then select checkout.<image>Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Click on the app icon for the browser to open it and access Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 838]}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/4806571780686350312_0.png", "training_data/AITW/aitw_images/webshopping/4806571780686350312_1.png" ]
7,297
[ { "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 usb-b to the cart on bestbuy, then select checkout.<image>Thought: Press home to exit the current app and return to the device's main screen.\nAction: {\"action\": \"PRESS HOME\", \"value\": null, \"position\": null}<image>Thought: Click on the app icon for the browser to open it and access Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 838]}<image>", "role": "user" }, { "content": "Thought: Scroll up to view the \"Go to Cart\" button for checking out.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/4806571780686350312_0.png", "training_data/AITW/aitw_images/webshopping/4806571780686350312_1.png", "training_data/AITW/aitw_images/webshopping/4806571780686350312_2.png" ]
7,298
[ { "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 usb-b to the cart on bestbuy, then select checkout.<image>Thought: Click on the app icon for the browser to open it and access Best Buy.\nAction: {\"action\": \"CLICK\", \"value\": null, \"position\": [367, 838]}<image>Thought: Scroll up to view the \"Go to Cart\" button for checking out.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}<image>", "role": "user" }, { "content": "Thought: Scroll up to see the \"Go to Cart\" button for proceeding with checkout.\nAction: {\"action\": \"SCROLL UP\", \"value\": null, \"position\": null}", "role": "assistant" } ]
[ "training_data/AITW/aitw_images/webshopping/4806571780686350312_1.png", "training_data/AITW/aitw_images/webshopping/4806571780686350312_2.png", "training_data/AITW/aitw_images/webshopping/4806571780686350312_3.png" ]
7,299