Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_987291ad-91f8-4e77-80b9-343575d7813d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is thomas.neo@gmail.com and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[input] -> TYPE: Anderson\n[input] -> TYPE: po box 2846\n[input] -> TYPE: Texas\n[button] Complete -> CLICK\n[button] Continue Shopping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.592, 0.185, 0.781, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a9a2e52-24b4-46c3-9e52-0f79c15ae3d0_a2f6493b-5528-4aeb-a97d-602877298c51.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK\n[button] Team -> CLICK\n[searchbox] Search -> CLICK\n[option] Finance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.607, 0.32, 0.621] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/02e7bae3-c67f-4227-b6ea-7b87d111202a_af9e9a40-200b-4453-83ce-3ff86dd64154.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show latest documentaries on Netflix and add the one with 70+ metascore.\nPrevious actions:\n[link] What to Watch on Netflix -> CLICK\n[button] Filter -> CLICK\n[button] Documentary -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.153, 0.31, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_6714117c-6959-4cbd-9ee2-9cd57f3d627d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[div] Belo Horizonte, Minas Gerais, Brazil -> CLICK\n[tab] Flexible dates -> CLICK\n[label] Weekend -> CLICK\n[div] May -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.898, 0.056, 0.97, 0.084] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e8637690-bb8c-4596-a608-5b40a29d77c9_93ff61b6-0bab-479c-9f06-45a4274258ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a large store in Washington that has kids' and maternity products, also check if they have a parking lot, and see the directions of the nearest store.\nPrevious actions:\n[link] Store Locator -> CLICK\n[input] -> CLICK\n[option] WA -> CLICK\n[button] Products -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.57, 0.412, 0.586] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_28771408-7ab1-41bd-9819-91f5781f65d7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[textbox] Drop-off location -> TYPE: 123 Main St, West Chicago, IL\n[heading] 123 Main St -> CLICK\n[button] pickup date input field -> CLICK\n[button] 29, March 2023 -> CLICK\n[button] pickup time input field -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.847, 0.313, 0.911, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03ac581c-ef95-4435-9d35-435e198b82de_6a5ae849-09da-452e-8f6b-7757dca46690.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the Emergency Sickness Plan policy certificates for Connecticut.\nPrevious actions:\n[button] Cars & Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.227, 0.812, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78915162-53c9-4cb1-86e1-6be6047528e0_63bb767f-b11f-4830-8208-0ee804fa1842.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out if Coldplay is playing any events in Columbus, OH on May 17.\nPrevious actions:\n[textbox] Search by team, artist, event or venue -> CLICK\n[textbox] Search by team, artist, event or venue -> TYPE: Coldplay\n[paragraph] Coldplay -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.157, 0.29, 0.255, 0.318] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1055658-7993-448c-9af6-a722cf69ff97_feb8be19-5f9b-44dc-a9fe-1467233b4677.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for the next restaurant-related event, only 1 ticket is needed.\nPrevious actions:\n[link] See more venues in the Special Events &amp; Experi... -> CLICK\n[link] HAPPY HOUR BURGER, Aria, Thursday, April 13, 2023 ... -> CLICK\n[combobox] 2 tickets for HAPPY HOUR BURGER -> SELECT: 1 Ticket" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.493, 0.153, 0.519] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_46f83ebb-597c-4df2-a715-6d17b102a7cd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[button] All cities -> CLICK\n[button] Go! -> CLICK\n[input] -> CLICK\n[div] All dates -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.387, 0.193, 0.419, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_442e1ce3-2522-48da-b947-c9d0c670411f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Los Angeles\n[span] , CA, USA -> CLICK\n[button] 1 NIGHT Sat, Apr 08 - Sun, Apr 09 -> CLICK\n[span] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.674, 0.194, 0.709, 0.214] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_45f168e4-68f7-4a40-b1cb-50e2d47ed9cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[div] 3 -> CLICK\n[checkbox] Free internet -> CLICK\n[button] Style -> CLICK\n[checkbox] Family -> CLICK\n[button] Amenities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.802, 0.081, 0.809] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_d05d5797-f2d2-4046-b3b3-8f19e5bbd1f3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, james.john@gmail.com. It is a family trip organized by Johnson.\nPrevious actions:\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK\n[link] Tickets, Passes, VIP Tours  -> CLICK\n[link] Group Tickets -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.621, 0.322, 0.656] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_771645db-3909-401b-9e11-ec577982b6c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[generic] 1 -> CLICK\n[generic] 4 -> CLICK\n[button] Search -> CLICK\n[button] Yes, I agree -> CLICK\n[span] Lowest price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.742, 0.183, 0.855, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b6316ee-4cfb-490e-bf52-9ee6cdded08b_d82a81d4-25cb-48d9-921d-0cc1a8624a2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find ideas and recommendation for things to do in Cancun.\nPrevious actions:\n[textbox] Where to? -> TYPE: cancun\n[circle] -> CLICK\n[span] Trip Inspiration -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.296, 0.055, 0.34, 0.064] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c4ab02e-a617-490d-96c6-333d7fa82fe9_acf51d07-4630-4160-999d-f3ecfe8a47a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of my upcoming trip with booking number 123456789 and last name Smith.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.224, 0.479, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_f1d36d0f-7896-44f3-bf48-6f9f9950416c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: Smithsonian\n[li] Smithsonian National Air and Space Museum, Indepen... -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.529, 0.339, 0.547] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/607cea69-abb5-4055-aa09-117650cb7cc9_821343aa-9c06-4f3c-9437-15e55f522c11.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request information for tickets for a group of 100 people at a park in california\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.393, 0.783, 0.457] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_69b85be2-186c-4be0-90bf-103fc674b6f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at jacksparrow@gmail.com.\nPrevious actions:\n[span] -> CLICK\n[button] Hiring Type -> CLICK\n[span] -> CLICK\n[combobox] Sort by -> SELECT: Most recent\n[span] Analyst - Sales Programs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.189, 0.325, 0.211] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_40a0c326-bcad-4edf-8b4e-6fb3af658ab1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] 1 room, 2 travelers -> CLICK\n[img] Decrease adults in room 1 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.273, 0.048, 0.283] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/130b1cd5-3e2f-4676-aea4-24ba9706171b_15606cb6-9b40-427c-b76c-5f32223fafda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the on demand sales section and rent a film in HD format.\nPrevious actions:\n[link] Visit the On Demand page -> HOVER\n[link] On Sale Now -> CLICK\n[img] movie poster for Elvis -> CLICK\n[button] Rent from $3.99 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.311, 0.174, 0.336] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_758947fe-0cd0-4b67-a5f6-62048e8f794a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[button] Year -> CLICK\n[button] 2010 -> CLICK\n[menuitem] 2018 -> CLICK\n[button] 2023 -> CLICK\n[menuitem] 2022 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.355, 0.249, 0.399] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_db4a2ab6-e43f-4059-9dfa-0e4c7fb2eeab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.083, 0.263, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eb609e15-ff10-4b3d-82ce-348c439548ca_d3e071fc-c039-46af-adab-d88fcba72fa8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[link] Girls -> CLICK\n[link] Jackets -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.432, 0.194, 0.445] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_34932950-fe34-4548-99d0-8a8726ddb9f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[listbox] hour -> SELECT: 10\n[listbox] minutes -> SELECT: 45\n[svg] -> CLICK\n[listbox] select adults -> SELECT: 2\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.404, 0.327, 0.438] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61c8e051-a847-4424-9d8b-b8bc2c134a35_c89c55cf-e379-47bd-b0b4-a642ffe7be1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the recent trades\nPrevious actions:\n[button] Shopping -> CLICK\n[link] Trades -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.178, 0.598, 0.193] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/af97084c-5b72-4fec-be1e-dcab0980b335_973418b6-859e-479f-8d1a-b1a8fa9c5e51.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check all Bayern Munich goalie stats\nPrevious actions:\n[button] MORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.364, 0.468, 0.406] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54d60a7c-f52d-4d79-b879-34698507e22c_83f96f84-7682-466e-a739-da6ce13c247e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[span] Albany, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[input] -> CLICK\n[gridcell] March 18, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.754, 0.283, 0.919, 0.321] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c50985ee-d4d0-4a9e-ac6f-97bede200abd_e8b587ce-c3a8-485f-8455-bc7869669484.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the lowest price ticket including fees to the next M3 Rock Festival - 2 Day Pass\nPrevious actions:\n[link] Music -> HOVER\n[link] Festivals -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.314, 0.105, 0.517, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2bce1096-f573-4752-94a9-e139ce37eb27_272ad721-8eb9-4e16-b522-ec352a3edc47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the list of off-Broadway theatre shows on April 19\nPrevious actions:\n[button] THEATRE -> CLICK\n[link] Off-Broadway -> CLICK\n[button] All dates -> CLICK\n[textbox] Select Date Range -> CLICK\n[gridcell] 19 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.721, 0.246, 0.904, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6c7934b-6949-46ee-8f72-edb46abd3da7_7713e50d-7086-49cf-a8ab-0cc3befbd494.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the winning odds in the Champions League for Real Madrid against Chelsea.\nPrevious actions:\n[span] Odds -> CLICK\n[heading] SOCCER -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.128, 0.25, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_57021f78-0a01-4b86-864a-5f427019edf4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[menuitem] Kids -> HOVER\n[menuitem] Pants & Leggings -> CLICK\n[div] Sports -> CLICK\n[link] Training -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.422, 0.233, 0.453] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4947d606-626e-4da3-a595-bfedacbed3ec_d1477074-827a-4194-a1bc-1c17e76b13c5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request ticket receipt for ticket no. 1234567890123 and last name Davis\nPrevious actions:\n[link] Receipts for tickets and fees -> CLICK\n[textbox] Ticket number -> CLICK\n[textbox] Ticket number -> TYPE: 1234567890123\n[textbox] Last name -> CLICK\n[textbox] Last name -> TYPE: Davis" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.575, 0.456, 0.683, 0.498] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd5d03cc-24a8-4284-ac43-b38579f416b1_a58ae00f-38de-4c81-a24f-d32bd6933d7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the status of flights between Abidjan and Accra.\nPrevious actions:\n[tab] Flight status -> CLICK\n[textbox] From / Flight number Autocomplete selection. Enter... -> TYPE: Abidjan\n[strong] Abidjan -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.201, 0.5, 0.253] in the image\nAnd my action is Action: TYPE\nValue: Accra" } ]

{ "bytes": "", "path": "./images/160fc162-7f03-4f59-83e1-5502d00806f2_1b586bab-28ee-4b81-96bd-0cce359c5989.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See what is playing on Showtime sorted by newest.\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[img] showtime -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.403, 0.355, 0.419] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_5bab90f5-78c2-4d19-82ab-2f2aabc94fb2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[checkbox] 24 May 2023 -> CLICK\n[checkbox] 28 May 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 9:30 AM\n[combobox] Drop off time -> SELECT: 9:00 AM\n[div] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.694, 0.134, 0.765, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_8528cae5-cd59-4742-b285-f1855866c552.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[span] Add -> CLICK\n[span] Add -> CLICK\n[path] -> CLICK\n[link] Fresh Vegetables -> CLICK\n[span] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.389, 0.367, 0.406] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_98e02390-fb4c-4887-9ec0-294167219c7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[textbox] Flight destination input -> TYPE: london\n[span] All airports -> CLICK\n[generic] Thursday April 20th -> CLICK\n[div] 23 -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.001, 0.453, 0.273, 0.488] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_cd7f794a-afd7-45b5-8d02-ed5fbce7caf5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[span] 0 -> TYPE: 7\n[tab] 7 -> CLICK\n[path] -> CLICK\n[div] 8+ -> CLICK\n[div] 3 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.61, 0.081, 0.618] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fb7741f6-f388-4535-903d-d07315ea995e_e41eb015-80b3-45b5-bc29-c9f672f163ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find fitness events for this weekend.\nPrevious actions:\n[link] Sports & Fitness -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.279, 0.252, 0.302] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_5391b73e-2ea7-472d-bbdf-0978e4e0564f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Arrival station, Sheffield selected. -> TYPE: manchester\n[span] Manchester -> CLICK\n[radio] Return -> CLICK\n[textbox] Date use format: 29-Mar-23 -> CLICK\n[link] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.153, 0.327, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_43bb051b-7c4e-4b20-921d-4555a8f353dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[link] Beauty Salons -> CLICK\n[input] -> TYPE: Seattle, WA\n[link] Seattle, WA -> CLICK\n[link] Seattle, WA -> CLICK\n[button] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.238, 0.074, 0.305, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fa2828c5-44b3-446e-ae42-a26438ed8343_e6d800be-8004-45eb-a793-b15400c0ccff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the upcoming departures for the oak grove station going southbound direction\nPrevious actions:\n[combobox] Search MBTA.com -> TYPE: oak grove station" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.845, 0.007, 0.87, 0.023] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ac35e5a5-f52f-4886-9a23-65f0a6492c5e_54a253e1-012d-435c-8ab1-277ef327c33f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find FC Barcelona's next fixture in the Spanish Copa de Rey\nPrevious actions:\n[li] Soccer -> HOVER\n[link] Barcelona -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.119, 0.093, 0.145] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_52c8c1af-9bd2-4aa9-aeca-c781ccba7366.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my parking space in Houston. Name: James Smith, Email: buckeye.foobar@gmail.com, phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[link] Rent My Parking Space -> CLICK\n[textbox] First Name * -> TYPE: James\n[textbox] Last Name * -> TYPE: Smith\n[textbox] Email * -> TYPE: buckeye.foobar@gmail.com\n[textbox] Phone * -> TYPE: 8888888888" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.645, 0.787, 0.673] in the image\nAnd my action is Action: SELECT\nValue: Chicago" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_76d2a3a9-6953-4102-b032-e0b0907c88e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, james.john@gmail.com. It is a family trip organized by Johnson.\nPrevious actions:\n[input] -> TYPE: James\n[input] -> TYPE: Johnson\n[input] -> TYPE: james.john@gmail.com\n[combobox] Organization Type -> SELECT: Family Trip\n[input] -> TYPE: Johnson" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.113, 0.777, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_10212b24-195e-48c9-acae-cb2350a78ceb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: SPRINGFIELD" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.194, 0.359, 0.217] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5e5f14-c875-4cfd-a517-175619491b90_3d497426-f9d7-4f13-a176-e700575969ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the NFL Scoreboard from the superbowl 2015\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.028, 0.128, 0.046] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_0e295f69-6563-427f-9cb9-163bc4c61253.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> TYPE: new orleans\n[span] New Orleans, Louisiana, United States -> CLICK\n[textbox] Drop-off location -> TYPE: new york\n[span] New York, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.557, 0.192, 0.694, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b332a3c6-c4f5-423c-a207-b1bcb28db6c3_fac64ba6-630f-443b-ae2f-0afb8aac89bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated Drop D guitar tab from the 1990s.\nPrevious actions:\n[link] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.366, 0.153, 0.384] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_464ce264-f475-4262-a089-2b8f06fc4f83.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[textbox] From -> TYPE: new york\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: washington\n[option] Washington, DC - Union Station (WAS) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.588, 0.137, 0.692, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_c45411de-bce5-415e-90d1-63f05c5810e1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Pet-Friendly -> CLICK\n[button] Road Trips -> CLICK\n[button] Last-Minute -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.244, 0.552, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_10e90e61-628c-4bc0-ab57-827dd4085228.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: abc@abc.com\nPrevious actions:\n[link] Careers -> CLICK\n[link] Sign up for job posting alerts -> CLICK\n[span] -> CLICK\n[button] Subscribe -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.711, 0.103, 0.977, 0.142] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_3f2a8087-9586-4576-82d5-aebc1c19025b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[link] Business Meetings  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.445, 0.336, 0.469] in the image\nAnd my action is Action: TYPE\nValue: new delhi" } ]

{ "bytes": "", "path": "./images/0b2c1886-0345-4ca7-a555-8b1cd1b1c40a_b60f4bf4-01db-45c4-99f2-28275b4807ec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse certified fresh sci-fi films streaming at home.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Certified fresh movies -> CLICK\n[svg] -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.482, 0.435, 0.502] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_4a105819-7709-498b-a943-5e3a9eefdfda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[combobox] Pick Up Time -> SELECT: 1:00 PM\n[combobox] Return Time -> SELECT: 2:00 PM\n[combobox] Select Residency -> SELECT: Vietnam\n[generic] Vehicle Type * -> CLICK\n[p] Small to Full Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.442, 0.25, 0.56, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51fce1f7-566e-4ae4-89a4-dea4d0ec569e_ae673ea3-b7f4-47ed-bf82-0f42f5cd51c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an available wine at Kroger.\nPrevious actions:\n[path] -> CLICK\n[button] Departments -> CLICK\n[link] Wine -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.259, 0.457, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff6ff6e5-e73c-4ba2-809e-59a1e269d68f_56a51491-e603-4275-841c-989da2b8d9fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Hair Loss Evaluation and Treatment in 10018 and show directions.\nPrevious actions:\n[button] Health -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.142, 0.504, 0.176] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2b1d94b-5309-4c9b-bcdd-8048172af7b5_4545e3b8-201f-4a29-b5e2-cd31dc104bb7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an foldable over-ear headphone under 35 USD in certified refurbished condition with lowest price + shipping.\nPrevious actions:\n[link] Headphones -> CLICK\n[link] Ear-Cup (Over the Ear) -> CLICK\n[button] Price -> CLICK\n[link] Under $35.00 -> CLICK\n[button] Condition -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.698, 0.24, 0.857, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5092fad7-ff8a-481e-bb0b-fe83590193ce_b802897f-2c52-42af-b317-321de287b5ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show reviews of top critics for lowest rated Tom Hanks work\nPrevious actions:\n[textbox] Search -> TYPE: Tom Hanks\n[p] Tom Hanks -> CLICK\n[link] My Life in Ruins (2009) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.435, 0.439, 0.518, 0.454] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_09dd0172-dd00-45b1-95e2-61dd15cf2d11.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[link] T red line bus commuter rail Zone 2 Braintree -> CLICK\n[combobox] To  -> TYPE: boston\n[span] Boston -> CLICK\n[button] Get trip suggestions -> CLICK\n[button] Depart at 8:40 AM, 4/10/23  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.318, 0.336, 0.33, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_9b22d165-4722-428c-a980-3773ac46b8d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[button] Kitchen -> CLICK\n[link] Kitchen Sinks -> CLICK\n[link] Drop In Two Bowl -> CLICK\n[checkbox] Ship to Home Eligible (97) -> CLICK\n[checkbox] Stainless Steel (75) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.17, 0.1, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_7abcc2cf-5142-4193-a68a-ccc119801db5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking with EV charging for month with lowest price in Chicago.\nPrevious actions:\n[tab] Monthly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.074, 0.785, 0.092] in the image\nAnd my action is Action: TYPE\nValue: Chicago" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_e89bb795-2d24-4e2c-bcae-1294e3501dfa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[button] close -> CLICK\n[heading] Same Day Delivery -> CLICK\n[link] Self-Rising Crust Uncured Pepperoni Frozen Pizza -... -> CLICK\n[svg] -> CLICK\n[link] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.748, 0.231, 0.988, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e12f51f6-c8c5-4a68-9586-d77927bca79c_b40a4626-a9b0-46f9-b9a6-35d49a8fd0bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a Tesla Shop Gift Card for April May with the email april.may@gmail.com to my cart\nPrevious actions:\n[link] Shop -> CLICK\n[menuitem] Lifestyle -> CLICK\n[img] Tesla Shop Gift Card -> CLICK\n[textbox] Name of Recipient -> TYPE: April May\n[textbox] Email Address of Recipient -> TYPE: april.may@gmail.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.679, 0.387, 0.938, 0.434] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8082086a-10a7-4631-9792-b57337426f9a_afbb5253-41d5-4896-8fb9-a49db36fecf7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a SUV with automatic transmission in New York drop off at March 30.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: New York\n[div] New York, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.1, 0.753, 0.132] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b4a2fc25-a7fe-4e31-beae-b31f2ef8cf3e_24676627-e890-4aab-a9a2-aa595ee4e950.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the list of games I've played recently.\nPrevious actions:\n[link] BUCKEYE.FOOBAR -> HOVER\n[link] GAMES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.134, 0.214, 0.253, 0.241] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d64cbfc6-7ace-4cad-9f0a-6643cd83de6e_5f310105-9322-4ff9-befc-9e9ada33ba05.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[i] -> CLICK\n[i] -> CLICK\n[region] 4 Stars & Up -> CLICK\n[link] $50 to $100 -> CLICK\n[span] Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.878, 0.077, 0.999, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd92cea9-a60f-4e09-90d7-32384ccdd61c_3d14978f-be25-44dd-b3f4-bf95d170d4f3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show most played games based on daily players.\nPrevious actions:\n[link] New & Noteworthy -> HOVER\n[link] Most Played -> CLICK\n[generic] By Current Players -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.143, 0.543, 0.158] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_43f569ad-2a06-4a74-b77c-16acd0431fcf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[textbox] To -> TYPE: bournemouth\n[span] Bournemouth -> CLICK\n[generic] 30 -> CLICK\n[div] -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.862, 0.414, 0.922, 0.451] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_2ec2117c-c501-416d-a25e-c24faef4c518.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Add to playlist -> CLICK\n[button] Add to playlist -> CLICK\n[button] Close -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.604, 0.361, 0.695, 0.378] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/839ad551-da04-4c8e-96c3-093e762ea167_b4ba7775-0761-4026-ace8-47325c692364.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and book the cheapest daytime only monthly parking option in Seattle near Stripe, 5th Avenue\nPrevious actions:\n[textbox] Search for parking -> TYPE: stripe, 5th avenue\n[li] Stripe, 5th Avenue, Seattle, WA, USA -> CLICK\n[tab] Monthly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.316, 0.161, 0.345] in the image\nAnd my action is Action: SELECT\nValue: Daytime Only Parking" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_31fe500d-c8ce-4a15-a225-c86333e8826a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Samsung-made and larger than 11-inch screen Android tablet, in the price range of 200 to 300 dollars and add it to the cart.\nPrevious actions:\n[link]  Electronics  -> CLICK\n[link] Tablets -> CLICK\n[img] Samsung -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.527, 0.158, 0.541] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_251bb8a8-5a58-4219-8fde-c24c613d4337.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.214, 0.512, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c4538b84-ca81-413a-8f3d-7ce87e42b4f6_98a07d01-547e-46a7-a19d-843c7cef225e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Saturday park hours for Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.225, 0.843, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5cb859d-8460-4b27-b6c9-d6fea6de9889_9abb2493-8fff-4950-9b8a-d371af9516a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find kids 13Y size t shirts and add 3 to cart.\nPrevious actions:\n[link] KIDS -> CLICK\n[link] T-Shirts -> CLICK\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.234, 0.463, 0.247] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f208b8b-6d5c-4d3f-8df0-cab24d29edda_6505d42e-3973-4cb2-9d59-b7fa6513d6c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find The Last of Us series and add it to my watch list.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: The Last of Us" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.029, 0.194, 0.064] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_6c2838cc-2eba-4e57-ba2b-91edc2804240.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[link] WOMEN -> CLICK\n[tab] Bottoms -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.086, 0.322, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31a74ae0-4b8a-407b-8f3d-a094a6966254_583fc711-90e0-4363-ac48-057b547a3a33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show books of Dr Seuss with price range of $20 to $40 and add 2 to basket.\nPrevious actions:\n[link] Shop by category∨ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.486, 0.155, 0.627, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8cb94647-b0a8-4b8c-b00a-4788ef522b79_60d9f7d8-adde-4e1a-8763-46cf48b62328.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.141, 0.271, 0.158] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_acf2309a-3542-43c5-a8cb-3fef021a5c0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[link] Hostels -> CLICK\n[searchbox] Please type your destination -> TYPE: udupi\n[option] Udupi Karnataka, India -> CLICK\n[span] 25 -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.793, 0.555, 0.805, 0.567] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/91f56f3b-e3de-4d57-95df-f976a11c64f7_cdaff30d-7164-4b7a-b1e2-a95d33da9282.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a veterinarian emergency service for dogs in Hawaii with a BBB rating of A+\nPrevious actions:\n[link] Veterinarians -> CLICK\n[input] -> TYPE: hawaii\n[link] Hawaii, HI -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.008, 0.867, 0.034] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd5d03cc-24a8-4284-ac43-b38579f416b1_ab2175cb-f9af-4c04-a557-c9671e492e76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the status of flights between Abidjan and Accra.\nPrevious actions:\n[tab] Flight status -> CLICK\n[textbox] From / Flight number Autocomplete selection. Enter... -> TYPE: Abidjan\n[strong] Abidjan -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: Accra" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.309, 0.72, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_7672056b-5964-4cb7-95fb-579dec1a1d72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.078, 0.129, 0.098] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3236b068-8eaf-4a39-913f-b71884a35c39_aaa64149-aeef-4b01-9d53-323f0c6357b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the most played games sorted by daily player count.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.096, 0.402, 0.106] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_b3044a24-aa62-41ae-a42c-b6ab256132f4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[link] Search for packages -> CLICK\n[textbox] From -> TYPE: Birmingham" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.24, 0.573, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdc94e3a-caa3-42b0-aa1b-b99f728f6292_cb226f96-18d8-4dd2-bad2-d38a23094374.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a demo drive for Model Y for Roy Adams with phone number 123-999-0000, email address RA@gmail.com and zip code 90001 in the United States.\nPrevious actions:\n[link] Demo Drive -> CLICK\n[button] Model Y -> CLICK\n[textbox] Last Name -> TYPE: Adams\n[textbox] First Name -> TYPE: Roy\n[textbox] Phone Number -> TYPE: 123-999-0000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.162, 0.733, 0.391, 0.748] in the image\nAnd my action is Action: TYPE\nValue: RA@gmail.com" } ]

{ "bytes": "", "path": "./images/bf008019-bffd-42ad-a48b-054488e1458c_384d2cb5-1500-4cfb-b973-ad828bf541fc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking near any NBA arena to enter today after 5 pm and exit after 8 pm\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.72, 0.087, 0.732] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_0f9aceb2-5773-43c0-883f-c3e0ab76df13.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: CDG\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] Depart , required. -> TYPE: 04/21/2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.399, 0.204, 0.409] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf8da12a-e1fd-48b5-8c53-b88f301ca1e0_04bab092-de15-4b34-8d45-a444c6e6b1b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for video game consoles and filter the results to show only those that have Wi-Fi Capability.\nPrevious actions:\n[link] Electronics -> CLICK\n[button] Video Games & Consoles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.405, 0.184, 0.414] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_689efb16-8afc-4054-ae22-289fba6674b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated romantic summer vacations in Spain\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.296, 0.486, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccf98191-100e-441a-93e8-8ff4076aeaa0_c99f7ced-46a0-4187-a323-0ce345af5b76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.005, 0.204, 0.04] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_72aaf637-cf0b-4762-beb3-e4cdfe50dbf8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[div] Europe -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] July -> CLICK\n[button] SEARCH DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.173, 0.266, 0.194] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2623c8-ce74-4572-9eb6-89d0b216d0cf_c07dee8e-5b45-432f-80b3-c79f3ff2f1d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow Taylor Swift and add a playlist to next up.\nPrevious actions:\n[searchbox] Search -> CLICK\n[searchbox] Search -> TYPE: Taylor Swift\n[button] Search -> CLICK\n[link] Taylor Swift -> CLICK\n[button] Follow -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.202, 0.375, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_1329c041-da50-44be-9694-0a50b5a51d2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\n[button] Departments -> HOVER\n[button] Electrical -> HOVER\n[link] Smart Home -> CLICK\n[link] Smart Lighting -> CLICK\n[button] Indoor Lighting (7) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.366, 0.089, 0.375] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_89cbd56a-b983-4a06-afa8-cfd121dd0ddd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[button] Sort: Best Match -> CLICK\n[link] Time: newly listed -> CLICK\n[button] Condition -> CLICK\n[link] Used -> CLICK\n[button] Style -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.712, 0.281, 0.868, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/22e33a38-902c-4f62-9e9a-822b2370b6d1_43a17e87-29ed-4e79-8b90-ede9013a6030.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Exotic Cars -> CLICK\n[link] Reserve Now -> CLICK\n[link] Beverly Hills -> CLICK\n[button] Selected Pick-Up Date 03/21/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.39, 0.177, 0.429, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9223ed29-5abb-4f4d-8108-1c3a584a7017_46a981ea-d3c6-42fb-9d9e-3cc0f679b56d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information about reduced bus fares.\nPrevious actions:\n[button] Fares  -> CLICK\n[link] Bus Fares -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.245, 0.576, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/59bdd427-c34b-4b93-a8b8-0c3a49acdcfa_4908afca-3881-4d5f-bc9c-d1bd00895602.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip flight from Santa Fe, New Mexico to Phoenix, Arizona for 1 adult on August 13th and returning on August 28th.\nPrevious actions:\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[span] 13 -> CLICK\n[span] 28 -> CLICK\n[button] Find flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.234, 0.497, 0.333] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d7ab9bf0-99e2-4f32-92c9-c1a10bc68f82_9b7e1386-5ab5-46e3-8739-701d711d5059.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check Manchester City Performance Stats of 2022/2023 season in the champions league\nPrevious actions:\n[link] ESPN Soccer Home Page -> HOVER\n[link] Champions League -> CLICK\n[link] Manchester City -> CLICK\n[link] Stats -> CLICK\n[select] English FA Community Shield -> SELECT: UEFA Champions League" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.189, 0.302, 0.26, 0.321] in the image\nAnd my action is Action: SELECT\nValue: 2022-23" } ]