Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 84

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track a bus leaving from Abbotsford.\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK\n[combobox] From -> TYPE: Abbotsford\n[div] Abbotsford -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.212, 0.98, 0.255] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[button] Greece -> CLICK\n[button] Athens -> CLICK\n[div] Apr -> CLICK\n[generic] 2 -> CLICK\n[div] May 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.124, 0.366, 0.175, 0.387] 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 washing machines available for free local pickup within 25 miles of zip code 90026.\nPrevious actions:\n[combobox] Search for anything -> TYPE: washing machine" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.786, 0.03, 0.917, 0.057] 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: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\n[link] Cancel my order -> CLICK\n[input] -> TYPE: James Smith\n[textbox] Email address used to place your order * -> TYPE: [email protected]\n[textbox] Order number * -> TYPE: X123456\n[textbox] Date you received your order (DD/MM/YY) * -> TYPE: 08/04/23" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.489, 0.759, 0.517] in the image\nAnd my action is Action: TYPE\nValue: Harry Potter Box Set" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[div] Sports -> CLICK\n[link] Training -> CLICK\n[div] Size -> CLICK\n[link] YXL -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.395, 0.233, 0.428] 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[heading] Continue -> CLICK\n[div] -> CLICK\n[div] -> CLICK\n[span] 36 -> CLICK\n[button] 34 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.635, 0.626, 0.774, 0.659] 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 NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[link] NFL -> CLICK\n[link] Scores -> CLICK\n[button] Calendar -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.14, 0.514, 0.154] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop 2-5 day cruises to the Caribbean from Miami during August 2023.\nPrevious actions:\n[button] Sail To -> CLICK\n[button] Caribbean -> CLICK\n[div] Sail From -> CLICK\n[button] Miami, FL -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.099, 0.551, 0.118] 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 climbing courses within 50 miles of 90028.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.455, 0.0, 0.552, 0.017] 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[textbox] Search by Name -> TYPE: all star stand up comedy\n[p] All Star Stand Up Comedy -> CLICK\n[link] View Tickets -> CLICK\n[span] Filters -> CLICK\n[listbox] Sort by Price - Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.855, 0.976, 0.896] 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 men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Mens -> CLICK\n[div] Product Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.387, 0.194, 0.396] 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 booking with ticket 123456 under the name James Buck.\nPrevious actions:\n[button] View / Modify / Cancel Reservation -> CLICK\n[textbox] Confirmation Number (required) -> TYPE: 123456\n[textbox] First Name (required) -> CLICK\n[textbox] First Name (required) -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.421, 0.833, 0.456] in the image\nAnd my action is Action: TYPE\nValue: Buck" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.691, 0.046, 0.987, 0.088] in the image\nAnd my action is Action: TYPE\nValue: Alinea" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 with the least amount of walking from Central Park Zoo to the Broadway Theater.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.179, 0.359, 0.199] in the image\nAnd my action is Action: TYPE\nValue: central park zoo" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 available tickets within $100 to $200 for the New York Knicks first game on April2 nd.\nPrevious actions:\n[textbox] Search by Name -> TYPE: New york knicks\n[p] New York Knicks -> CLICK\n[link] View Tickets -> CLICK\n[span] (0) -> CLICK\n[textbox] Max Price -> TYPE: 200" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.435, 0.826, 0.468] in the image\nAnd my action is Action: TYPE\nValue: 100" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cruises to Hawaii departing from Los Angeles in January 2024 with a duration of 12 days.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.363, 0.285, 0.444] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with 4 star and above rating in Los Angeles for 3 days next week and save it.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Los Angeles\n[span] City -> CLICK\n[div] 21 -> CLICK\n[div] 23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.948, 0.139, 0.964, 0.154] 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 things to do nearby in Mar 30, 202\n3\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.157, 0.463, 0.165] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hotels in Tokyo for two adults and one child, with a budget of $500 per night for 2 nights starting on May 5th.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[generic] Japan -> CLICK\n[div] 5 -> CLICK\n[div] 7 -> CLICK\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.3, 0.686, 0.329] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[link] 25, Saturday March 2023 -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Rail -> CLICK\n[label] Express Bus -> CLICK\n[button] Done button - Press enter key to submit travel pre... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.208, 0.359, 0.237] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find theaters for Creed III within 20 miles of zip code 90028.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.378, 0.161, 0.62, 0.527] 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 eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[img] -> CLICK\n[link] Produce -> CLICK\n[link] Fresh Fruits -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.455, 0.149, 0.516, 0.164] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate vehicle price with a challenge credit score, monthly payment of $250 with a $3000 down payment and 24% APR for 48 months in Tennessee.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.014, 0.323, 0.05] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[div] May -> CLICK\n[span] -> CLICK\n[span] Filters -> CLICK\n[textbox] max price $ -> TYPE: 100\n[div] Shared room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.667, 0.401, 0.786, 0.439] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the top restaurants in Boston to reserve for april 22?\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.101, 0.223, 0.119] 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 wireless keyboard and mouse combo under $100.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless keyboard mouse\n[button]  -> CLICK\n[textbox] price to -> TYPE: 100\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.498, 0.365, 0.701, 0.406] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest action tv shows which are rated fresh by both the audience and the rotten tomatoes\nPrevious actions:\n[div] -> CLICK\n[button] APPLY -> CLICK\n[span] Audience score -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.258, 0.643, 0.276] 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: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.903, 0.396, 0.944] 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 kids 13Y size t shirts and add 3 to cart.\nPrevious actions:\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK\n[svg] -> CLICK\n[img] AIRism Cotton Graphic Short-Sleeve Raglan T-Shirt -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.337, 0.802, 0.37] 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 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[span] -> CLICK\n[button] Show all 25 -> CLICK\n[span] -> CLICK\n[button] Sort by:Top picks for solo travellers -> CLICK\n[button] Price (lowest first) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.803, 0.242, 0.913, 0.257] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a rental car in Miami, FL for pick up at the airport and drop off at a different location within the same city.\nPrevious actions:\n[link] Search for cars -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.093, 0.414, 0.11] 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 refund status for John Davis for ticket no. 1234567890123\nPrevious actions:\n[link] Check the status of a refund -> CLICK\n[textbox] Ticket number -> CLICK\n[textbox] Ticket number -> TYPE: 1234567890123\n[textbox] First name -> CLICK\n[textbox] First name -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.256, 0.691, 0.302] 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 winter coats featured in the weekly ad and is at least 15% off.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: winter coat\n[button] go -> CLICK\n[button] Deals -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.86, 0.426, 0.988, 0.448] 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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[link] Products -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.474, 0.32, 0.497] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip flight from Santa Fe, New Mexico to Phoenix, Arizona for 1 adult on August 13th and returning on August 28th.\nPrevious actions:\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: Phoenix\n[button] Phoenix, AZ, US (PHX) -> CLICK\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[span] 13 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.603, 0.391, 0.635] 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[svg] -> CLICK\n[tab] One-way -> CLICK\n[svg] -> CLICK\n[button] Increment -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.147, 0.432, 0.182] 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: check Manchester City Performance Stats of 2022/2023 season in the champions league\nPrevious actions:\n[link] ESPN Soccer Home Page -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.507, 0.097, 0.663, 0.113] 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 weekly chart-topper artist and play the number 1 track of that artist after liking the track.\nPrevious actions:\n[link] Charts -> CLICK\n[link] Weekly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.149, 0.185, 0.209, 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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[combobox] Return Time -> SELECT: 9:00 AM\n[button] Select My Car -> CLICK\n[link] Recommended -> CLICK\n[link] Price (Low to High) -> CLICK\n[link] Pay Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.62, 0.777, 0.651] 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[img] -> CLICK\n[link] Close -> CLICK\n[button] Instant Quote -> CLICK\n[textbox] What city would you like to depart from? -> TYPE: Chicago\n[checkbox] I'm interested in the reverse trip of the selected... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.771, 0.316, 0.797] 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: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[label] L -> CLICK\n[heading] Color -> CLICK\n[label] BLACK -> CLICK\n[svg] -> CLICK\n[heading] Supima® Cotton V-Neck Short-Sleeve T-Shirt (2022 E... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.815, 0.178, 0.843, 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: Find map for the KCCR airport\nPrevious actions:\n[input] -> CLICK\n[input] -> TYPE: KCCR" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.046, 0.576, 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: Find a pair of mens running shoes in black, size 7 extra wide, 4+ stars and under $50 and add them to my cart\nPrevious actions:\n[textbox] Search Amazon -> TYPE: mens black running shoes" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.651, 0.008, 0.686, 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: Look for a recently posted part-time Job in Gamestop stores in Fresno, California, and apply.\nPrevious actions:\n[link] Careers -> CLICK\n[link] View Jobs Stores -> CLICK\n[button] State / Province -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.245, 0.307, 0.277] 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 JetBlue press releases for the year 2020\nPrevious actions:\n[link] Press RoomExternal Link should open in a new windo... -> CLICK\n[link] View All Releases  -> CLICK\n[combobox] Select year: -> SELECT: 2020" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.347, 0.336, 0.48, 0.37] in the image\nAnd my action is Action: SELECT\nValue: Press Releases" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[strong] Accra -> CLICK\n[option] One way -> CLICK\n[gridcell] 14 April 2023 -> CLICK\n[button] Continue -> CLICK\n[button] Show flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.621, 0.727, 0.766] 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] Change Location -> CLICK\n[textbox] Enter ZIP or State -> CLICK\n[textbox] Enter ZIP or State -> TYPE: 07470\n[button] set store -> CLICK\n[button] Distance & Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.195, 0.234, 0.213] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Exotic Cars -> CLICK\n[link] Reserve Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.564, 0.118, 0.575] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to national parks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.525, 0.941, 0.579] 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[textbox] Date use format: 29-Mar-23 -> CLICK\n[link] 2 -> CLICK\n[textbox] Date use format: -> CLICK\n[link] 2 -> CLICK\n[listbox] hour -> SELECT: 17" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.341, 0.327, 0.37] 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 luxury trip deal anywhere to go in spring\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.106, 0.492, 0.151] 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 activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\n[path] -> CLICK\n[combobox] Search by city or activity -> TYPE: Miami\n[generic] United States -> CLICK\n[button] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.063, 0.307, 0.08] 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 all time most popular solo track by ArianaGrande\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: Ariana Grande\n[button] Search -> CLICK\n[a] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.477, 0.645, 0.487] 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 one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[button] Remove -> CLICK\n[textbox] Flight origin input -> TYPE: Mumbai\n[span] Chhatrapati Shivaji Intl -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.458, 0.136, 0.59, 0.168] in the image\nAnd my action is Action: TYPE\nValue: Dubai" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy TV shows streaming on HBO Max that was released in 2010.\nPrevious actions:\n[link] What to Watch on HBO Max -> CLICK\n[button] Filter -> CLICK\n[button] Comedy -> CLICK\n[button] TV Shows -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.337, 0.639, 0.357] 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 fully electric car pickup at Athens Airport (ATH) Sat, Apr 1, 2023 and return to the same palce at Mon, Apr 3, 2023.\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: Athens" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.128, 0.366, 0.145] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK\n[img] Woods 41366 Surge Protector with Overload Safety F... -> CLICK\n[span] Qty: -> CLICK\n[option] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.709, 0.275, 0.869, 0.287] 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 Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[link] Find Stores -> CLICK\n[button] enter zip or city, state -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.481, 0.322, 0.639, 0.348] 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 flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[div] May 2023 -> CLICK\n[div] Apr -> CLICK\n[div] Choose date -> CLICK\n[generic] 5 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.862, 0.405, 0.922, 0.442] 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.163, 0.241, 0.172] 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 low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.077, 0.036, 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: Check the movie \"65\" that is digital at the AMC Grove City 14 showing at 7:30 pm on Tuesday, March 28, 2023 and buy four tickets for seats J10 through J7\nPrevious actions:\n[select] AMC Grove City 14 -> SELECT: AMC Grove City 14\n[select] All Movies -> SELECT: 65\n[select] Sun, Mar 26 -> SELECT: Tue, Mar 28\n[link] 7:30pm -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.438, 0.832, 0.473, 0.879] 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 highest rated romantic summer vacations in Spain\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Spain" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.091, 0.89, 0.107] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] 1, Saturday, April 2023. Available. Select as chec... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.394, 0.777, 0.435] 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] 6 -> CLICK\n[combobox] Pick Up Time -> SELECT: 11:00 AM\n[textbox] mm/dd/yyyy -> CLICK\n[select] June 2023 -> SELECT: June 2023\n[link] 10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.326, 0.891, 0.365] in the image\nAnd my action is Action: SELECT\nValue: 1 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: Find unique experiences in London of maximum one hour duration which are rated four stars and above\nPrevious actions:\n[textbox] Where to? -> TYPE: London\n[button] London England -> CLICK\n[circle] -> CLICK\n[link] Unique Experiences -> CLICK\n[label] Up to 1 hour -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.575, 0.236, 0.59] 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 flight from London to New York on 9th May.\nPrevious actions:\n[tab] Flights -> CLICK\n[combobox] Flying from -> TYPE: London\n[option] Destination London -> CLICK\n[combobox] Flying to -> TYPE: New York\n[option] Destination New York (NY) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.507, 0.521, 0.52] 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 rail for Oyster Bay, Provincetown.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.201, 0.132, 0.263, 0.171] 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 economy flight from Pune to New York in June and select the fully refundable.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: Pune" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.216, 0.359, 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: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.662, 0.192, 0.67] 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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[span] Mar 18 -> CLICK\n[button] 20th March (Monday) -> CLICK\n[combobox] Time -> SELECT: 8:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.474, 0.546, 0.535] in the image\nAnd my action is Action: SELECT\nValue: 4 guests" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 scores of the premiership on 19th of March.\nPrevious actions:\n[span] Scores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.679, 0.048, 0.72, 0.076] 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 reggae concerts this weekend.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.112, 0.045, 0.205, 0.082] 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 black strollers within $100 to $250.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: black stroller\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.146, 0.146, 0.155, 0.153] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular guitar tab for Absolute Beginners.\nPrevious actions:\n[link] Tabs -> CLICK\n[svg] -> CLICK\n[link] Most popular of all time -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.28, 0.153, 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: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Jackets -> CLICK\n[div] Sports -> CLICK\n[link] Outdoor -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.701, 0.233, 0.747] 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 deals for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to popular destinations -> CLICK\n[textbox] Input departure airport -> TYPE: New York\n[textbox] Input arrival airport -> TYPE: Honolulu" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.253, 0.492, 0.287] 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 wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[link] Bras -> CLICK\n[heading] Category -> CLICK\n[input] -> CLICK\n[option] Relaxed Wireless -> CLICK\n[heading] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.145, 0.256, 0.158] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Premium Cars available to rent at LondonHeathrow Airport.\nPrevious actions:\n[label] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: London" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.153, 0.429, 0.188] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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[span] Santa Fe, New Mexico, United States -> CLICK\n[div] 16 -> CLICK\n[div] 18 -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.948, 0.096, 0.964, 0.107] 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 gift shops available at a park in New York\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.368, 0.783, 0.401] 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 best VIP seat to the Red Hot Chili Peppers 2023 Tour\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER\n[link] Jazz -> CLICK\n[img] Image for Red Hot Chili Peppers 2023 Tour -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.209, 0.372, 0.239] 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 truck for 10001 zip code on Sunday 11:30 am with flexible dates.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 23 -> CLICK\n[input] -> CLICK\n[span] -> CLICK\n[button] Find Your Truck -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.309, 0.915, 0.338] 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 woman t-shirt in xl size from merchandise section, add 2 pieces to the cart and check out.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.418, 0.846, 0.479, 0.857] 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 Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[img] Hasbro -> CLICK\n[button] All Filters -> CLICK\n[tab] Character -> CLICK\n[checkbox] Hulk -> CLICK\n[tab] Year Manufactured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.251, 0.443, 0.26] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[heading] Sweatpants -> CLICK\n[checkbox] PINK -> CLICK\n[checkbox] XXL -> CLICK\n[input] -> CLICK\n[option] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.347, 0.906, 0.374] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 31 -> CLICK\n[link] 7 -> CLICK\n[button] Select My Car -> CLICK\n[generic] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.232, 0.567, 0.256] 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 trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[textbox] From -> CLICK\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.09, 0.554, 0.101] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.493, 0.359, 0.536] 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 Playstation gift card of $10.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.058, 0.646, 0.078] in the image\nAnd my action is Action: TYPE\nValue: playstation gift card $10" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Build Your Own Custom PC Build Your Own Cu... -> CLICK\n[link]  CPU -> CLICK\n[button] START A NEW BUILD -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.367, 0.868, 0.379] 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 reservation availability for an Indian restaurant with price below $30 in East village\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.069, 0.615, 0.08] 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 artist Mark Knight from London and follow him and add his most liked track to next up.\nPrevious actions:\n[searchbox] Search -> TYPE: Mark Knight" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.541, 0.007, 0.553, 0.014] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\n[link] Find a receipt -> CLICK\n[radio] Confirmation or eTicket number -> CLICK\n[textbox] Confirmation or eTicket More information about con... -> TYPE: 12345678\n[textbox] First name -> TYPE: Jason\n[textbox] Last name -> TYPE: Two" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.326, 0.271, 0.356] 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[combobox]  -> SELECT: 2 Adults\n[combobox]  -> SELECT: 1 Child\n[select] Age -> SELECT: 0\n[link] Search Hotels -> CLICK\n[radio] $100 to $200 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.37, 0.123, 0.376] 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 spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Customer Service -> CLICK\n[div] Need an extra part? -> CLICK\n[link] Read more -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.364, 0.218, 0.386] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for used Jaguar XFs with no black exterior color and save the search as Jaguar to get a notification daily.\nPrevious actions:\n[textbox] Ex. Black exterior -> TYPE: black\n[button] Black (Exterior Color) -> CLICK\n[button] SAVE SEARCH -> CLICK\n[textbox] Custom name your search -> TYPE: Jaguar\n[button] CONTINUE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.427, 0.293, 0.459, 0.314] 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 most expensive cruise deals in Europe and Mediterranean.\nPrevious actions:\n[link] Cruises -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.672, 0.161, 0.984, 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: Buy the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[img] -> CLICK\n[radio] 5 -> CLICK\n[radio] GRADE_A -> CLICK\n[button] Add To Cart -> CLICK\n[link] Confirm Membership to Checkout -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.294, 0.209, 0.325] in the image\nAnd my action is Action: TYPE\nValue: Joe" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[textbox] From -> TYPE: New York\n[option] New York City area (NYC) -> CLICK\n[textbox] To -> TYPE: Aruba\n[option] Aruba (AUA) -> CLICK\n[span] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.624, 0.315, 0.658, 0.349] in the image\nAnd my action is Action: CLICK" } ]