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 the initial release date for Guardians of the Galaxy Vol. 3 the movie.\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Search -> TYPE: Guardians of the Galaxy\n[tab] MOVIES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.286, 0.677, 0.345] 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 Bayern Munich goalie stats\nPrevious actions:\n[button] MORE -> CLICK\n[div] Soccer -> CLICK\n[div] Bundesliga -> CLICK\n[div] Bayern Munich -> CLICK\n[heading] STATS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.51, 0.242, 0.564, 0.298] 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 movie trailers currently in theaters with \"fresh\" rating.\nPrevious actions:\n[link] MOVIES -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.439, 0.302, 0.587, 0.316] 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 highest-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[link] Home Services -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.076, 0.474, 0.096] 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[gridcell] Choose Saturday, April 22nd 2023. It's available. -> CLICK\n[gridcell] Choose Tuesday, April 25th 2023. It's available. -> CLICK\n[button] 1 Room, 2 Guests Click to edit rooms and guests -> CLICK\n[path] -> CLICK\n[button] sub 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.47, 0.279, 0.486, 0.288] 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 status of flights between Abidjan and Accra.\nPrevious actions:\n[tab] Flight status -> CLICK\n[textbox] From / Flight number Autocomplete selection. Enter... -> TYPE: Abidjan" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.124, 0.5, 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: View the upcoming schedule from Otis St@Summer St to City Point of the transit near South Station for today.\nPrevious actions:\n[tab] Schedules -> CLICK\n[span] Transit Near Me -> CLICK\n[input] -> TYPE: South Station\n[option] South Station, 700 Atlantic Ave, Boston, MA 02110,... -> CLICK\n[link] Go to route -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.138, 0.284, 0.379, 0.308] 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 full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> 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, 0.363, 0.29, 0.38] 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: Locate a large store in Washington that has kids' and maternity products, also check if they have a parking lot, and see the directions of the nearest store.\nPrevious actions:\n[link] Store Locator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.207, 0.416, 0.238] 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 train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[listbox] hour -> SELECT: 08\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK\n[div] -> CLICK\n[heading] to next step -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.242, 0.371, 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: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[combobox] Party of 2 -> SELECT: 7 Guests\n[svg] -> CLICK\n[button] View more availability for Canal Street Eatery & M... -> CLICK\n[button] 2:00 PM Eatery -> CLICK\n[button] Reserve Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.277, 0.523, 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: Find map for the KCCR airport\nPrevious actions:\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.022, 0.576, 0.032] in the image\nAnd my action is Action: TYPE\nValue: KCCR" } ]

[ { "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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[span] Mar 18 -> CLICK\n[button] 20th March (Monday) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.447, 0.546, 0.5] in the image\nAnd my action is Action: SELECT\nValue: 8 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: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[link] Playlists -> CLICK\n[link] NEW PLAYLIST -> CLICK\n[button] START FROM SCRATCH -> CLICK\n[h1] My New Playlist -> CLICK\n[h1] My New Playlist -> TYPE: Dirty" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.303, 0.524, 0.385, 0.547] 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 all time popular drop c rock tab of beginner difficulty\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.031, 0.176, 0.039] 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 round-trip bus tickets from Houston to Dallas leaving on May 7th and returning a week later.\nPrevious actions:\n[input] -> CLICK\n[button] Next month -> CLICK\n[gridcell] May 07, 2023 -> CLICK\n[input] -> CLICK\n[gridcell] May 14, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.274, 0.831, 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: 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[searchbox] Enter ZIP or State -> TYPE: 08817\n[button] Search for CarMax stores. -> CLICK\n[button] set store -> CLICK\n[link] Shop -> CLICK\n[link] SHOP ALL CARS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.245, 0.249, 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: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[textbox] Check In  -> CLICK\n[link] 24 -> CLICK\n[textbox] Sun Mar 26  -> CLICK\n[link] 27 -> CLICK\n[combobox]  -> SELECT: 1 Room" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.466, 0.161, 0.556, 0.203] in the image\nAnd my action is Action: SELECT\nValue: 2 Adults" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: london\n[span] London -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: sheffield\n[span] Sheffield -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.263, 0.194, 0.291] 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 pasta restaurant in Sydney and save it\nPrevious actions:\n[button] Location Columbus, OH -> CLICK\n[button] Sydney -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: pasta" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.149, 0.026, 0.657, 0.06] 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 car guide info for economy car and reserve.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Car Guides -> CLICK\n[link] Vehicle Info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.343, 0.337, 0.365] 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 crossbows on sale with limited stock.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Crossbows and Accessories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.286, 0.103, 0.305] 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 named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] Electronic -> CLICK\n[img] Madonna -> CLICK\n[link] Like A Virgin -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.175, 0.77, 0.185] 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[textbox] Vehicle Price -> CLICK\n[textbox] Vehicle Price -> TYPE: 10000\n[textbox] Down Payment -> CLICK\n[textbox] Down Payment -> TYPE: 500\n[combobox] State -> SELECT: New Jersey" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.447, 0.459, 0.485] in the image\nAnd my action is Action: SELECT\nValue: Challenged (< 580 FICO® Score)" } ]

[ { "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 Romantic Audio fiction books with the lowest price.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Audio Books -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.431, 0.196, 0.461] 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 a rental car to pick up at Paris Charles de Gaulle Airport CDG on april 13 at 10 am and drop off on april 18 at the same time\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: Paris Charles de Gaulle Airport (CDG)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.142, 0.366, 0.161] 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\n[searchbox] To -> TYPE: 74th street, brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.326, 0.359, 0.352] 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 recent NFL-related videos.\nPrevious actions:\n[link] National Football League NFL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.698, 0.044, 0.729, 0.065] 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 Wheelchair accessible parking for April 09 event in Barclays Center that allows entry after 10am\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.068, 0.67, 0.085] in the image\nAnd my action is Action: TYPE\nValue: Barclays Center" } ]

[ { "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: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[button]  -> CLICK\n[gridcell] Tue, May 30, 2023 -> CLICK\n[gridcell] Thu, Jun 1, 2023 -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.426, 0.336, 0.453] in the image\nAnd my action is Action: TYPE\nValue: 1" } ]

[ { "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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.007, 0.348, 0.022] 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 places that serve burgers in 44012 zip code and sort the results by highest rated\nPrevious actions:\n[textbox] Find -> TYPE: Burgers\n[span] Burgers -> CLICK\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: 44012\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.101, 0.63, 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 flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[svg] -> CLICK\n[label] Points -> CLICK\n[link] Sort & Filter -> CLICK\n[button] Default   -> CLICK\n[span] Price by Core -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.213, 0.817, 0.227] 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: Schedule a virtual consultation for Solar Roof. The name is James Smith. The address is 123 st rd. The emial address is [email protected]\nPrevious actions:\n[link] Solar Roof -> CLICK\n[link] Schedule a virtual consultation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.432, 0.355, 0.444] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

[ { "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 user reviews for the game \"Cyberpunk 2077\"\nPrevious actions:\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.121, 0.677, 0.141] in the image\nAnd my action is Action: TYPE\nValue: Cyberpunk 2077" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View travel credits for the passenger Leon Sin with the record locator jcqnhd ans ticket number 1234567\nPrevious actions:\n[searchbox] Search AA.com® -> TYPE: travel credit\n[searchbox] Search AA.com® -> ENTER\n[heading] Find your trip - Find a reservation - American Air... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.121, 0.176, 0.363, 0.214] in the image\nAnd my action is Action: TYPE\nValue: sin" } ]

[ { "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 cafes that have outdoor seating and is dog friendly.\nPrevious actions:\n[span] Cafe -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK\n[checkbox] Outdoor Seating -> CLICK\n[checkbox] Dogs Allowed -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.46, 0.688, 0.491] 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 two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: NIAGRA FALLS\n[option] Niagara Falls, ON, Canada -> CLICK\n[button] 1 NIGHT Sun, Apr 09 - Mon, Apr 10 -> CLICK\n[span] 17 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.88, 0.181, 0.915, 0.2] 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: Plan a trip from Greenport to Oyster Bay Branch, starting with train and ending via bus with less than 1/2 mile walk.\nPrevious actions:\n[listitem] Greenport, NY, USA -> CLICK\n[searchbox] To -> TYPE: Oyster Bay\n[listitem] Oyster Bay, NY, USA -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[combobox] Start Journey -> SELECT: Train" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.396, 0.318, 0.61, 0.338] in the image\nAnd my action is Action: SELECT\nValue: Bus" } ]

[ { "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 discount black insulated hunting boots for Men with average ratings over 3.5 stars\nPrevious actions:\n[label] Boots -> CLICK\n[label] Sale -> CLICK\n[div] Color -> CLICK\n[label] Black -> CLICK\n[div] Average Ratings -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.179, 0.088, 0.193] 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: Need the cheapest small car on April 7, 10 am at Auckland airport for pick-up, return will be on April 10 at approx 5 pm.\nPrevious actions:\n[span] Auckland Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 7 -> CLICK\n[combobox] Pick Up Time -> SELECT: 10:00 AM\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.529, 0.424, 0.557, 0.443] 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 one-way flights from New York to Toronto.\nPrevious actions:\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.318, 0.259, 0.361] 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: find kinect camera for xbox one.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: kinect camera\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.285, 0.179, 0.422] 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 quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight origin input -> TYPE: NEW YORK\n[span] All airports -> CLICK\n[textbox] Flight destination input -> TYPE: PARIS" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.49, 0.127, 0.84, 0.159] 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 all the women cropped tops with lowest price first.\nPrevious actions:\n[link] WOMEN -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.117, 0.362, 0.127] 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 quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[tab] One-way -> CLICK\n[svg] -> CLICK\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight origin input -> TYPE: NEW YORK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.182, 0.573, 0.228] 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 quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[textbox] *Preferred date of travel -> CLICK\n[link] 22 -> CLICK\n[button] Continue -> CLICK\n[div] + -> CLICK\n[textbox] About Your Trip: -> TYPE: Wedding Anniversary" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.522, 0.451, 0.582] 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 Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[path] -> CLICK\n[textbox] Zip Code -> TYPE: 60538\n[link] Store Locator   -> CLICK\n[textbox] Zip Code -> TYPE: 60538\n[button] Search By Zip Code -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.591, 0.109, 0.612] 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 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[link] Gifting -> CLICK\n[link] Gift Cards -> CLICK\n[div] Send a physical card through the mail. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.638, 0.287, 0.706, 0.312] in the image\nAnd my action is Action: TYPE\nValue: 50" } ]

[ { "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 educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Video Games -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.269, 0.085, 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: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[p] SUV / Crossover -> CLICK\n[textbox] ZIP -> TYPE: 10017\n[button] Search -> CLICK\n[combobox] Select Minimum Year -> SELECT: 2022\n[combobox] Select Maximum Year -> SELECT: 2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.406, 0.235, 0.427] in the image\nAnd my action is Action: SELECT\nValue: 50 mi" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the winning odds in the Champions League for Real Madrid against Chelsea.\nPrevious actions:\n[span] Odds -> CLICK\n[heading] SOCCER -> CLICK\n[heading] ENGLISH PREMIER LEAGUE -> CLICK\n[link] UEFA CHAMPIONS LEAGUE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.55, 0.061, 0.604, 0.083] 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 five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[link] New York City New York, USA -> CLICK\n[button] Select Activities -> CLICK\n[span] Cultural Tours -> CLICK\n[span] Any -> CLICK\n[li] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.296, 0.347, 0.316] in the image\nAnd my action is Action: TYPE\nValue: 75" } ]

[ { "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 events in Los Angeles and select the one on the Friday this weekend.\nPrevious actions:\n[button] CITY GUIDES -> HOVER\n[link] Los Angeles -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.3, 0.881, 0.316] 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 cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[link] 26 -> CLICK\n[polyline] -> CLICK\n[span] Youth -> CLICK\n[combobox] Select passenger age -> SELECT: 16\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.17, 0.133, 0.185] in the image\nAnd my action is Action: SELECT\nValue: 12" } ]

[ { "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[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> 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, 0.386, 0.29, 0.414] 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: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[link] Beverage Packages -> CLICK\n[img] -> CLICK\n[link] Beverage Packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.234, 0.331, 0.352, 0.351] 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 terms and conditions of Amtrak RideReserve for Multi-Ride Passes\nPrevious actions:\n[button] DEALS -> CLICK\n[link] MULTI-RIDES & RAIL PASSES USA Rail passes, monthly... -> CLICK\n[img] -> CLICK\n[link] EXPLORE MULTI-RIDE PASSES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.509, 0.413, 0.737, 0.431] 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 for places to stay in Santa Fe, New Mexico for a weekend starting on Jun 16th for 3 guests and 2 rooms.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Santa Fe" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.153, 0.573, 0.194] 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[div] Destination or property -> TYPE: jakarta\n[hp-input-button] Destination or property -> TYPE: jakarta\n[div] Jakarta, Special Capital Region of Jakarta -> CLICK\n[div] Choose date -> CLICK\n[div] Jun -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.192, 0.171, 0.206] 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 flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[checkbox] 12 May 2023 -> CLICK\n[button] Search -> CLICK\n[button] Choose your room -> CLICK\n[link] Choose Another Hotel -> CLICK\n[button] Choose your room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.233, 0.335, 0.308, 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: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[input] -> CLICK\n[div] All dates -> CLICK\n[span] -> CLICK\n[span] 1 -> CLICK\n[div] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.572, 0.229, 0.689, 0.248] 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 top 50 Movies and TV shows by Sci fi genre.\nPrevious actions:\n[path] -> CLICK\n[span] Top 250 Movies -> CLICK\n[link] Sci-Fi -> CLICK\n[button] Open Navigation Drawer -> CLICK\n[span] Top 250 TV Shows -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.645, 0.691, 0.67, 0.701] 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 trade-in options for PS4.\nPrevious actions:\n[link] repeat Trade-In -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.258, 0.428, 0.435, 0.569] 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 score of the latest nfl game played by the las vegas raiders.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.219, 0.028, 0.728, 0.051] in the image\nAnd my action is Action: TYPE\nValue: las vegas raiders" } ]

[ { "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 next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[listitem] Queensboro Plaza Station, Long Island City, NY, US... -> CLICK\n[searchbox] To -> TYPE: Grand Central, NY\n[listitem] Grand Central Terminal, East 42nd Street, New York... -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.235, 0.609, 0.272] 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 3 movies from At the Kiosk which are new to Wishlist.\nPrevious actions:\n[link] Navigate to at-the kiosk -> HOVER\n[link] select to navigate to New -> CLICK\n[img] Missing (2023) -> CLICK\n[button] Click to add title to wishlist. -> CLICK\n[link] Navigate to at-the kiosk -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.057, 0.115, 0.085, 0.123] 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 hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[link] Shop Hotels -> CLICK\n[button] Going to -> TYPE: New Delhi\n[button] New Delhi Delhi, India -> CLICK\n[button] Check-out April 25, 2023 -> CLICK\n[button] Apr 26, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.929, 0.377, 0.984, 0.409] 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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[button] Locations -> HOVER\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: washington" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.193, 0.514, 0.203] 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 Jazz music genre albums and tracks.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.005, 0.681, 0.023] 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 most expensive things to do anywhere in December in a map\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Things To Do -> CLICK\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.303, 0.161, 0.372, 0.195] 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[button] 2023 -> CLICK\n[menuitem] 2017 -> CLICK\n[button] Back to all categories -> CLICK\n[button] Features -> CLICK\n[listitem] Sunroof(s) (2) Sunroof(s) (2) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.204, 0.249, 0.23] 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 empire builder route in West US part of heartland and check the Minnesota stop.\nPrevious actions:\n[button] DESTINATIONS -> CLICK\n[polygon] -> CLICK\n[button] Heartland -> CLICK\n[link] The page with details for The Heart of America wil... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.386, 0.686, 0.485, 0.71] 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 south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.008, 0.561, 0.035] in the image\nAnd my action is Action: TYPE\nValue: SOUTH AFRICAN HISTORY PODCAST" } ]

[ { "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 adventure movies coming to theaters.\nPrevious actions:\n[link] MOVIES -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.364, 0.238, 0.382] 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 travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: JFK\n[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[textbox] Depart , required. -> TYPE: 04/23/2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.71, 0.42, 0.895, 0.461] 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 journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[radio] Return -> CLICK\n[textbox] Date use format: 29-Mar-23 -> CLICK\n[link] 2 -> CLICK\n[textbox] Date use format: -> CLICK\n[link] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.237, 0.265, 0.257] in the image\nAnd my action is Action: SELECT\nValue: 17" } ]

[ { "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 one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: addis ababa\n[strong] Addis Ababa -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: accra\n[strong] Accra -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.267, 0.634, 0.29] 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 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[combobox] Distance -> SELECT: 100 Miles\n[combobox] Minimum Year -> SELECT: 2018\n[combobox] Maximum Year -> SELECT: 2018\n[button] Make  -> CLICK\n[checkbox] Honda (549) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.302, 0.277, 0.31] 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 the most recent full time Accounting & Finance Job available in Richmond, Virginia.\nPrevious actions:\n[textbox] Search for Job title -> TYPE: Accounting\n[link] Accounting & Finance 7 jobs -> CLICK\n[button] State -> CLICK\n[span] Virginia -> CLICK\n[button] City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.458, 0.137, 0.477] 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 one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[span] Faro -> CLICK\n[textbox] To -> TYPE: bournemouth\n[span] Bournemouth -> CLICK\n[generic] 30 -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.12, 0.953, 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: Request information for tickets for a group of 100 people at a park in california\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.554, 0.846, 0.602] 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 bus stops in Alanson, MI\nPrevious actions:\n[button] Explore -> CLICK\n[link] Bus stops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.173, 0.142, 0.182] 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 tables at Chianti - MG Road restaurant on March 30,1:30 PM for 4 Guests.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: CHIANTI\n[combobox] Guests -> SELECT: 4 Guests\n[button] March 30, 2023. Selected date. -> CLICK\n[button] 1:30 PM Dining Room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.463, 0.523, 0.492] 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 price of Tesla Model Y Performance for the 10001 zip code.\nPrevious actions:\n[link] Model Y -> CLICK\n[link] Order Now -> CLICK\n[div] Dual Motor All-Wheel Drive -> CLICK\n[button] 43235 -> CLICK\n[input] -> TYPE: 10001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.236, 0.286, 0.395, 0.305] 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 the balance sheet and cash flow statement for the fiscal year 2021 of Six Flags.\nPrevious actions:\n[link] Investors -> CLICK\n[link] Financial Info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.245, 0.867, 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 the lowest price ticket for All star stand up comedy event happen 6pm on the 25th March 2023.\nPrevious actions:\n[link] concerts. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.229, 0.294, 0.257] in the image\nAnd my action is Action: TYPE\nValue: all star stand up comedy" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for the next restaurant-related event, only 1 ticket is needed.\nPrevious actions:\n[link] See more venues in the Special Events &amp; Experi... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.234, 0.186, 0.246] 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.155, 0.072, 0.208, 0.09] 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 next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[searchbox] From -> TYPE: Queensboro plaza\n[listitem] Queensboro Plaza Station, Long Island City, NY, US... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.169, 0.359, 0.185] in the image\nAnd my action is Action: TYPE\nValue: Grand Central, NY" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[link] Gloucester -> CLICK\n[link] Plan a trip from this station -> CLICK\n[combobox] To  -> TYPE: NORTH PLYMOUTH\n[em] Plymouth -> CLICK\n[button] Depart at 8:20 AM, 4/10/23  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.318, 0.482, 0.343, 0.5] 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.03, 0.361, 0.055] 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:\n[searchbox] Search by ZIP code or city, state -> TYPE: atlanta georgia\n[button] Submit -> CLICK\n[span] Select store -> CLICK\n[button] Show more filters modal -> 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 [0.942, 0.167, 0.977, 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: Find the cheapest new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[option] automatic trash can lid -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 60\n[button] Submit price range -> CLICK\n[input] -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.686, 0.075, 0.775, 0.088] 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 available opportunities for a volunteer event for year 2023\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.869, 0.0, 0.945, 0.023] 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 tour to the statue of liberty for 3 adult on march 27th\nPrevious actions:\n[link] tours. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.295, 0.269, 0.31] 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 round trip from Phoenix to Miami with maximum budget of $2000.\nPrevious actions:\n[combobox] Flying from -> TYPE: Phoenix" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.308, 0.31, 0.316] 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: Schedule a virtual consultation for Solar Roof. The name is James Smith. The address is 123 st rd. The emial address is [email protected]\nPrevious actions:\n[textbox] First Name -> TYPE: James\n[div] -> TYPE: Smith\n[input] -> TYPE: 123st rd\n[textbox] Email Address -> TYPE: [email protected]\n[checkbox] Solar Roof -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.89, 0.365, 0.914] 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 cheapest vitamin C and D to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.283, 0.02, 0.328, 0.038] 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[checkbox] 5 June 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[tab] Fastest -> CLICK\n[button] See flight -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.559, 0.786, 0.591] in the image\nAnd my action is Action: CLICK" } ]