Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "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[button] - -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.345, 0.263, 0.354] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[generic] Site Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.101, 0.196, 0.124] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[button] Shopping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.332, 0.033, 0.42, 0.046] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 map of a Six flags park in mexico\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags México -> CLICK\n[button] Go! -> CLICK\n[link] Planea Tu Visita  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.813, 0.118, 0.967, 0.126] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 schedule and maps for the orange line\nPrevious actions:\n[link] subway Subway Lines -> CLICK\n[span] Orange Line -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.105, 0.281, 0.128] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[button] 1 Room, 2 Guests Click to edit rooms and guests -> CLICK\n[path] -> CLICK\n[button] sub 1 -> CLICK\n[div] open -> CLICK\n[option] 6 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.351, 0.677, 0.374] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 direct flight From mumbai to new delhi, India, on june 1 and return travel on june 8.\nPrevious actions:\n[tab] Flights -> CLICK\n[generic] Round-trip -> CLICK\n[combobox] Flying from -> TYPE: MUMBAI\n[option] Airport Chhatrapati Shivaji Maharaj International ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.184, 0.764, 0.194] in the image\nAnd my action is Action: TYPE\nValue: NEW DELHI" } ]

[ { "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 [email protected].\nPrevious actions:\n[link] Open Jobs -> CLICK\n[span] -> CLICK\n[button] Country -> CLICK\n[span] -> CLICK\n[button] State / Province -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.348, 0.218, 0.359] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[textbox] Pickup -> CLICK\n[button] Saturday, April 8, 2023 -> CLICK\n[button] Thursday, April 13, 2023 -> CLICK\n[combobox] Pickup time Selected 10:00 a.m. -> CLICK\n[combobox] Pickup time Selected 10:00 a.m. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.76, 0.266, 0.8] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[gridcell] 8 June 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[button] Show all 14 -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.251, 0.157, 0.261] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\n[combobox] Search products and services -> TYPE: zyrtec\n[button] Search for zyrtec -> CLICK\n[img] Zyrtec 24 Hour Allergy Relief Tablets with 10 mg C... -> CLICK\n[button] Check More Stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.715, 0.102, 0.881, 0.118] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

[ { "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: What are the top restaurants in Boston to reserve for april 22?\nPrevious actions:\n[path] -> CLICK\n[button] Boston -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.379, 0.655, 0.406] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] New York -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: 66 perry st\n[span] 66 -> CLICK\n[span] Apr 18 -> CLICK\n[gridcell] 20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.096, 0.718, 0.112] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 a deal which is highly rated in Fiji location.\nPrevious actions:\n[textbox] Where? -> TYPE: Fiji\n[div] Fiji -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.085, 0.266, 0.101] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.048, 0.566, 0.059] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 favorites a cruise from San Francisco to the Panama Canal departing Oct 2024\nPrevious actions:\n[span] Sail To -> CLICK\n[button] Panama Canal -> CLICK\n[span] Sail From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.417, 0.274, 0.438] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[img] -> CLICK\n[span] Add to list -> CLICK\n[checkbox] Walgreens New -> CLICK\n[button] Done -> CLICK\n[button] Back -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.668, 0.193, 0.704] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 most expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\n[link]  Gaming & VR  -> HOVER\n[link] PS5 Accessories -> CLICK\n[generic] Controller -> CLICK\n[span] Sony -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.372, 0.192, 0.39] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 status of flight 6944 on April 6\nPrevious actions:\n[link] Flight status -> CLICK\n[span] Flight number -> CLICK\n[spinbutton] Flight number , required. -> CLICK\n[spinbutton] Flight number , required. -> TYPE: 6944\n[combobox] Date -> SELECT: Thursday, April 6" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.301, 0.875, 0.315] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.19, 0.584, 0.325, 0.598] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights one way -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.29, 0.29, 0.309] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 rental car in Miami, FL for pick up at the airport and drop off at a different location within the same city.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Miami Airport\n[span] Miami -> CLICK\n[textbox] Drop-off location -> CLICK\n[textbox] Drop-off location -> TYPE: Miami\n[span] Miami, Florida, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.944, 0.101, 0.963, 0.112] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 new surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[link] New -> CLICK\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK\n[img] Woods 41366 Surge Protector with Overload Safety F... -> CLICK\n[span] Qty: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.807, 0.314, 0.857, 0.329] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Alaska -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.166, 0.447, 0.209] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 rental cars in Seattle, WA and filter the results by the Best score.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.068, 0.181, 0.085] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[link] Careers -> CLICK\n[link] here -> CLICK\n[checkbox] Engineering (41 items) -> CLICK\n[checkbox] Spain (18 items) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.727, 0.092, 0.738] in the image\nAnd my action is Action: CLICK" } ]

[ { "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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.189, 0.177, 0.21] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 list of all movies that are being released in May 2023\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.573, 0.047, 0.591] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[div] Multi-city -> CLICK\n[span] Sat 13 May -> CLICK\n[checkbox] 1 June 2023 -> CLICK\n[span] Where from? -> TYPE: TOKYO\n[span] TYO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.385, 0.127, 0.666, 0.146] in the image\nAnd my action is Action: TYPE\nValue: NEW DELHI" } ]

[ { "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[checkbox] SUV -> CLICK\n[svg] -> CLICK\n[div] -> CLICK\n[checkbox] Avis -> CLICK\n[button] More filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.285, 0.813, 0.3, 0.822] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 comedy shows taking place in Chicago, IL and expand the results once.\nPrevious actions:\n[button] Change Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.097, 0.432, 0.231, 0.453] in the image\nAnd my action is Action: TYPE\nValue: Chicago" } ]

[ { "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 a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[span] Westminster -> CLICK\n[checkbox] Offers Takeout -> CLICK\n[button] Thai -> CLICK\n[button] See all -> CLICK\n[checkbox] All staff fully vaccinated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.517, 0.154, 0.529, 0.165] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 queen-size pillow protectors from the Marriot shop, and if found, add two pieces to the cart and checkout.\nPrevious actions:\n[link] Shop Marriott Opens a new window -> CLICK\n[menuitem] category pillows -> CLICK\n[span] Pillow Protector -> CLICK\n[combobox] Select a Size -> SELECT: Queen\n[spinbutton] Main item quantity -> TYPE: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.69, 0.407, 0.96, 0.444] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 car toll rate for bridges and tunnels\nPrevious actions:\n[span] Menu -> CLICK\n[span] Agencies -> CLICK\n[link] Bridges & Tunnels -> CLICK\n[div] Tolls by vehicle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.325, 0.367, 0.447] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Mark a review in the best rated activity to do in Paris in May 12, 2023 as he\nlpful\nPrevious actions:\n[gridcell] Fri May 12 2023 -> CLICK\n[circle] -> CLICK\n[svg] -> CLICK\n[span] Traveler Rating -> CLICK\n[img] 4.5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.165, 0.159, 0.179] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: Boston\n[span] Boston -> CLICK\n[svg] -> CLICK\n[button] 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.661, 0.177, 0.855, 0.212] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

[ { "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 prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[img] Driscoll's Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.03, 0.159, 0.05] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.245, 0.699, 0.275] in the image\nAnd my action is Action: TYPE\nValue: Doja Cat" } ]

[ { "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[button] Lowest Regular Rate -> CLICK\n[label] Senior Discount -> CLICK\n[button] Find Hotels -> CLICK\n[combobox] Sort by: -> CLICK\n[option] Guest Rating -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.127, 0.266, 0.249, 0.289] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 women's hiking boots section and filter the results to show only those that are waterproof and have a rating of at least 4 stars and size 6.\nPrevious actions:\n[button] Camp & Hike -> HOVER\n[link] Women's -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.828, 0.082, 0.842] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 schedule for Long Island Rail Road & Metro-North Railroad from Bay Shore to Breakneck Ridge on Thu, Mar 23, 08:37 AM.\nPrevious actions:\n[span] Breakneck Ridge -> CLICK\n[button] 03/18/2023 -> CLICK\n[link] 23, Thursday March 2023 -> CLICK\n[select] 1 -> SELECT: 8\n[select] 00 -> SELECT: 37" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.797, 0.309, 0.854, 0.339] in the image\nAnd my action is Action: SELECT\nValue: AM" } ]

[ { "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 a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: bali\n[generic] Indonesia -> CLICK\n[gridcell] Sat Apr 01 2023 -> CLICK\n[button] 4 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.177, 0.393, 0.188] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Join the waitlist for a ticket for the Hackney Clothes Swap - Earth Day event being held on April 22nd. Name: Joe Bloggs. Email: [email protected]\nPrevious actions:\n[div] Search for events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.174, 0.418, 0.209] in the image\nAnd my action is Action: TYPE\nValue: Hackney" } ]

[ { "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 copy of the Gorillaz first studio album.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.006, 0.467, 0.041] in the image\nAnd my action is Action: TYPE\nValue: gorillaz" } ]

[ { "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 vacation packages to Hawaii.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.194, 0.181, 0.233] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 women's sports wear, size S.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: sports wear\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.23, 0.277, 0.328, 0.292] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[span] Birmingham -> CLICK\n[checkbox] Return to a different location -> CLICK\n[searchbox] Return Location (ZIP, City or Airport) (required) -> TYPE: MONTGOM\n[span] Montgom -> 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 [0.315, 0.347, 0.354, 0.381] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 French best sellers under $40 available in digital that are currently in stock.\nPrevious actions:\n[link] Bestsellers -> CLICK\n[select] All -> SELECT: US$20 to US$40\n[select] All -> SELECT: In stock (53476)\n[select] All -> SELECT: Digital" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.239, 0.196, 0.26] in the image\nAnd my action is Action: SELECT\nValue: French (299)" } ]

[ { "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 service options for cars under warranty.\nPrevious actions:\n[button] Open helpful links menu -> CLICK\n[link] Service & Repairs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.422, 0.155, 0.491, 0.179] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 software requirements for iPhones that support live tv on demand streaming.\nPrevious actions:\n[link] Navigate to on-demand -> HOVER\n[link] select to navigate to Supported Devices -> CLICK\n[generic] FREE LIVE TV -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.261, 0.388, 0.273, 0.402] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.152, 0.005, 0.491, 0.033] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[link] Registry -> CLICK\n[button] Find a registry -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.17, 0.321, 0.37, 0.362] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[radio] Owned -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.328, 0.284, 0.353] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[div] Columbus, OH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.203, 0.347, 0.224] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[button] Country -> CLICK\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK\n[button] Team -> CLICK\n[searchbox] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.459, 0.29, 0.473] in the image\nAnd my action is Action: CLICK" } ]

[ { "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] Back to all categories -> CLICK\n[button] Fuel Type -> CLICK\n[listitem] Gas (45) Gas (45) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.274, 0.234, 0.296] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[generic] 4 -> CLICK\n[button] Search -> CLICK\n[button] Yes, I agree -> CLICK\n[span] Lowest price -> CLICK\n[button] Choose room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.166, 0.863, 0.191] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 details of the fastest trip between 52nd Street,Brooklyn and 74th Street, Brooklyn, leaving now, that is accessible for a disabled person.\nPrevious actions:\n[searchbox] From -> TYPE: 52nd street, brooklyn\n[listitem] 52nd Street, Brooklyn, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.245, 0.359, 0.269] in the image\nAnd my action is Action: TYPE\nValue: 74th street, brooklyn" } ]

[ { "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 Railcard options for a 20 year old couple traveling within London and the South East\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK\n[menuitem] Railcards -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.226, 0.311, 0.244] in the image\nAnd my action is Action: SELECT\nValue: 18-25" } ]

[ { "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 tickets from Edinburgh Waverly to Glagsgow Central on May 18, leaving nearest 3PM for 1 adult with a Veterans Railcard\nPrevious actions:\n[textbox] Date use format: 17-Mar-23 -> CLICK\n[path] -> CLICK\n[link] 18 -> CLICK\n[listbox] hour -> SELECT: 15\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.362, 0.16, 0.377] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: What are the popular online Health events for tomorr\now?\nPrevious actions:\n[link] Health -> CLICK\n[heading] Most popular events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.255, 0.153, 0.27] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 29 -> CLICK\n[link] 28 -> CLICK\n[combobox] Pick Up Time -> SELECT: 9:00 AM\n[combobox] Return Time -> SELECT: 9:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.442, 0.217, 0.56, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 Golden State Warriors Player List.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.931, 0.041, 0.966, 0.069] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 cheapest bus for 2 persons from New York to Washington, DC.\nPrevious actions:\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Washington\n[span] Washington, DC -> CLICK\n[span] -> CLICK\n[button] Find tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.642, 0.324, 0.781, 0.338] in the image\nAnd my action is Action: SELECT\nValue: Price" } ]

[ { "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 the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK\n[button] Update Search -> 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, 0.41, 0.339, 0.439] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[tab] Flights -> CLICK\n[tab] One-way -> CLICK\n[button] Leaving from -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.137, 0.362, 0.172] in the image\nAnd my action is Action: TYPE\nValue: jfk" } ]

[ { "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 flights from New York City to London and filter the results to show only non-stop flights.\nPrevious actions:\n[textbox] Flight origin input -> TYPE: New York City\n[input] -> CLICK\n[textbox] Flight destination input -> CLICK\n[textbox] Flight destination input -> TYPE: London\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.944, 0.125, 0.963, 0.139] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[textbox] From (type text or use the arrow keys) -> TYPE: albany\n[span] Albany, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.341, 0.277, 0.413, 0.285] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 reviews for best electric SUV and find the 1 star rated review and mark it helpful.\nPrevious actions:\n[link] Car Reviews -> HOVER\n[link] Best Cars -> CLICK\n[img] Best SUVs image -> CLICK\n[div] SUVs -> CLICK\n[link] See Details -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.122, 0.443, 0.131] in the image\nAnd my action is Action: CLICK" } ]

[ { "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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.108, 0.111, 0.446, 0.123] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

[ { "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: Join the waitlist for a ticket for the Hackney Clothes Swap - Earth Day event being held on April 22nd. Name: Joe Bloggs. Email: [email protected]\nPrevious actions:\n[combobox] autocomplete -> TYPE: Hackney\n[div] Hackney -> CLICK\n[combobox] autocomplete -> CLICK\n[combobox] autocomplete -> TYPE: Hackney\n[div] London, UK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.229, 0.326, 0.268] in the image\nAnd my action is Action: TYPE\nValue: Hackney Clothes Swap - Earth Day" } ]

[ { "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 used BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\n[listitem] BMW (389) BMW (389) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Model -> CLICK\n[listitem] X5 (87) X5 (87) -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.948, 0.087, 1.002, 0.115] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to national parks -> CLICK\n[heading] Southeast Region -> CLICK\n[link] Within sight of downtown Miami, yet worlds away, B... -> CLICK\n[link] Fly to Miami (MIA) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.536, 0.287, 0.633] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[link] 15 -> CLICK\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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.22, 0.782, 0.237] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[RootWebArea] Women's, Men's & Kids' Clothing & Accessories | UN... -> CLICK\n[searchbox] Search by keyword -> TYPE: women t-shirts\n[div] WOMEN / Tops -> CLICK\n[gridcell] Size -> CLICK\n[label] S -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.413, 0.152, 0.432, 0.163] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[link] Off-Broadway -> CLICK\n[button] All dates -> CLICK\n[textbox] Select Date Range -> CLICK\n[gridcell] 19 -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.529, 0.111, 0.553] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 vehicle at New York JFK International Airport May 2-May 5 for an owner above 25 years.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.173, 0.84, 0.195] in the image\nAnd my action is Action: TYPE\nValue: New York JFK" } ]

[ { "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 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Exterior Color -> CLICK\n[listitem] Black (1) Black (1) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.403, 0.243, 0.412] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: BRISTOL\n[span] Bristol Airport (By Bus) -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: LONDON\n[span] London Paddington -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.442, 0.15, 0.471, 0.164] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: las vegas\n[span] Las Vegas, NV -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: san francisco\n[span] San Francisco, CA -> CLICK\n[textbox] Departure -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.152, 0.233, 0.182, 0.259] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[button] Locations -> CLICK\n[link] Find a Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.222, 0.657, 0.263] in the image\nAnd my action is Action: TYPE\nValue: laguardia airport" } ]

[ { "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[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[button] Show all 25 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.463, 0.263, 0.48] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[button] Remove -> CLICK\n[span] New York, United States -> CLICK\n[textbox] Flight destination input -> TYPE: london\n[span] All airports -> CLICK\n[generic] Thursday April 20th -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.28, 0.354, 0.3] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[link] SEARCH CARS -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Change Location -> CLICK\n[textbox] Enter ZIP or State -> CLICK\n[textbox] Enter ZIP or State -> TYPE: 07470" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.534, 0.194, 0.709, 0.219] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.837, 0.945, 0.874] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 events in Lubbock, Texas during next 7 days\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.218, 0.782, 0.26] in the image\nAnd my action is Action: CLICK" } ]

[ { "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[link] Collectibles -> CLICK\n[button] Antiques -> CLICK\n[link] Furniture -> CLICK\n[link] Chairs -> CLICK\n[button] Sort: Best Match -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.735, 0.274, 0.923, 0.3] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 English Reading and Writing skills Educational Books for Ages 6-8 currently in stock that are available in hardback under 20$.\nPrevious actions:\n[link] Education -> CLICK\n[span] English Language -> CLICK\n[link] English Language: Reading & Writing Skills -> CLICK\n[select] All -> SELECT: In Stock (41,088)\n[select] All -> SELECT: Hardback (13,067)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.232, 0.196, 0.248] in the image\nAnd my action is Action: SELECT\nValue: Under US$20" } ]

[ { "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 flights between SFO and EWR using the Boeing 787-9 aircraft\nPrevious actions:\n[div] San Francisco Int'l (San Francisco) - -> CLICK\n[textbox] Destination -> CLICK\n[textbox] Destination -> TYPE: EWR\n[div] Newark Liberty Intl (Newark) - -> CLICK\n[img] Submit Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.427, 0.204, 0.437] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Send a message to Joe Bloggs who has the username 'boredcelt'.\nPrevious actions:\n[button] Community -> CLICK\n[link] Find Users -> CLICK\n[link] User Search -> CLICK\n[textbox] Enter First name, last name, and/or username: -> TYPE: Joe Bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.617, 0.13, 0.645, 0.145] in the image\nAnd my action is Action: CLICK" } ]

[ { "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-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.027, 0.67, 0.05] in the image\nAnd my action is Action: TYPE\nValue: mirror" } ]

[ { "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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Price -> CLICK\n[button] $10,000 -> CLICK\n[menuitem] $20,000 -> CLICK\n[button] $56,000 + -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.13, 0.254, 0.24, 0.281] in the image\nAnd my action is Action: CLICK" } ]

[ { "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: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[link] Trade In -> CLICK\n[link] Trade in by mail -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.243, 0.732, 0.286] in the image\nAnd my action is Action: TYPE\nValue: Nemo Front Porch 2P Tent" } ]

[ { "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\n[button] search -> CLICK\n[link] T orange line bus commuter rail Zone 1A Oak Grove -> CLICK\n[link] Go to route -> CLICK\n[button] View upcoming departures -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.305, 0.497, 0.342] in the image\nAnd my action is Action: SELECT\nValue: SOUTHBOUND Forest Hills" } ]

[ { "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 tickets for the Buckeyes football game on April 15th for a group of 5 people.\nPrevious actions:\n[link] BUY TICKETS -> CLICK\n[span] -> CLICK\n[label] 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.927, 0.232, 0.982, 0.255] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.223, 0.795, 0.231] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[div] Search -> CLICK\n[div] Premium -> CLICK\n[svg] -> CLICK\n[span] -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.224, 0.331, 0.237] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\n[tab] Things to do -> CLICK\n[textbox] Things to do in -> TYPE: singapore\n[button] Singapore Singapore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.115, 0.75, 0.136] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[tab] Flights -> CLICK\n[tab] One-way -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] 2 travelers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.129, 0.828, 0.137] in the image\nAnd my action is Action: CLICK" } ]

[ { "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 me the cheapest red Model Y available to register in 94043\nPrevious actions:\n[link] Model Y -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.155, 0.276, 0.175] in the image\nAnd my action is Action: CLICK" } ]