Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[label] Less than $100 -> CLICK\n[span] Sort by: -> CLICK\n[div] Price (Low to High) -> CLICK\n[label] In Stock -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.713, 0.087, 0.735] 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[span] 4831 Granite Dr -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[select] April 2023 -> SELECT: June 2023\n[link] 6 -> CLICK\n[combobox] Pick Up Time -> SELECT: 11:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.241, 0.691, 0.269] 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 wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[label] Purpose of your event -> CLICK\n[li] Wedding -> CLICK\n[textbox] Destination -> TYPE: Venice Beach\n[menuitem] Venice Beach, Los Angeles, CA, USA -> CLICK\n[textbox] Event space -> TYPE: 100" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.341, 0.48, 0.355] 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: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[searchbox] Search -> TYPE: Selena Gomez\n[button] Search -> CLICK\n[link] Selena Gomez -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.134, 0.171, 0.149] 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 safety rating for 2012 Honda Civic\nPrevious actions:\n[link] Price New/Used -> CLICK\n[combobox] Year -> SELECT: 2012\n[generic] Your Opinion Counts! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.599, 0.172, 0.612, 0.182] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[combobox] List -> SELECT: New\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] List Explorer -> CLICK\n[link] Manage My Lists -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.252, 0.046, 0.266] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[span] Boston -> CLICK\n[svg] -> CLICK\n[button] 18 -> CLICK\n[combobox] Time -> SELECT: 5:00 PM\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.234, 0.095, 0.448, 0.136] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[span] 11 -> CLICK\n[span] 18 -> CLICK\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK\n[checkbox] Motel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.486, 0.12, 0.633, 0.142] 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.126, 0.573, 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: Find Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[link] Find Stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.371, 0.168, 0.509, 0.187] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the external solid state drives available with lowest price first.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] See All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.546, 0.285, 0.572] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[button] Leaving from -> CLICK\n[textbox] Leaving from -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: changi" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.222, 0.652, 0.258] 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 monthly parking rates near the Museum of Modern Art.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: MOMA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.308, 0.748, 0.324] 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 black blazer for men with L size and add to wishlist.\nPrevious actions:\n[option] MEN -> CLICK\n[svg] -> CLICK\n[heading] Color -> CLICK\n[span] BLACK -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.23, 0.313, 0.248, 0.331] 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 the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: HOLLYWOOD" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.232, 0.795, 0.245] 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 Gingerbread cakes recipe and add ingredients to cart.\nPrevious actions:\n[textbox] Search -> TYPE: Gingerbread cakes\n[link] gingerbread cakes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.107, 0.227, 0.175, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find 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[checkbox] 20 June 2023 -> CLICK\n[span] 2 adults -> CLICK\n[button] - -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.689, 0.263, 0.705] 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 person by phone number 123456789.\nPrevious actions:\n[link] Find People -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.625, 0.126, 0.874, 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: Look for a room at the Marriott Bonvoy resort in the Caribbean for a 10-day stay starting on May 5th.\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Carribbean\n[button] 1 NIGHT Wed, Apr 19 - Thu, Apr 20 -> CLICK\n[span] 5 -> CLICK\n[span] 15 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.835, 0.594, 0.912, 0.633] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the best rated ukulele tab to my favorites\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: ukulele\n[b] ukulele -> CLICK\n[link] Tab -> CLICK\n[link] High rated -> CLICK\n[link] Far Cry 3 - Ukulele Girl -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.852, 0.101, 0.98, 0.126] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 3 in Los angeles for diner at 09 PM on Mar 10\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: diner\n[heading] Spiral Diner & Bakery - Fort Worth -> CLICK\n[combobox] Guests -> SELECT: 3 Guests\n[div] Today -> CLICK\n[button] March 10, 2023. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.243, 0.383, 0.35, 0.42] 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 price quote for new Kia Carnival for 11101.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.0, 0.605, 0.03] 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 a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[button] Next -> CLICK\n[input] -> TYPE: Crew" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.099, 0.525, 0.119] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the 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\n[link] The Weeknd -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.146, 0.39, 0.171, 0.403] 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[textbox] Search Amazon -> TYPE: surge protector\n[button] surge protector -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.16, 0.107, 0.167] 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.109, 0.713, 0.121] in the image\nAnd my action is Action: TYPE\nValue: Athens" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[combobox] From -> TYPE: columbus\n[button] Columbus, OH, US (CMH) -> CLICK\n[combobox] To -> TYPE: new orleans\n[button] New Orleans, LA, US (MSY) -> CLICK\n[textbox] Depart date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.376, 0.132, 0.407] 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: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[button] Explore (current) -> CLICK\n[link] Africa 29 -> CLICK\n[div] Durban -> CLICK\n[link] Discover -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.058, 0.59, 0.279, 0.64] in the image\nAnd my action is Action: TYPE\nValue: doha" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the list of critic reviews for the movie Creed III.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: creed III" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.15, 0.047, 0.657, 0.128] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[button] Tuesday April 11, 2023 -> CLICK\n[svg] -> CLICK\n[checkbox] Free internet -> CLICK\n[button] Amenities -> CLICK\n[checkbox] Casino -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.724, 0.089, 0.735] 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[span] Mar 18 -> CLICK\n[button] 20th March (Monday) -> CLICK\n[combobox] Time -> SELECT: 8:00 PM\n[combobox] Size -> SELECT: 4 guests\n[button] Update search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.48, 0.095, 0.57, 0.136] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a dome tent to my shopping cart.\nPrevious actions:\n[link] Camping -> CLICK\n[menuitem] View All -> CLICK\n[div] Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.596, 0.064, 0.607] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[p] SUVs & Wagons -> CLICK\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $21.99/Day -> CLICK\n[checkbox] $13.00/Day -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.812, 0.311, 0.93, 0.343] 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 tickets for events in Boston.\nPrevious actions:\n[button] CITY GUIDES -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.66, 0.094, 0.782, 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: Find a music party in Ohio and follow its organizer\nPrevious actions:\n[div] Search for events -> CLICK\n[textbox] Search events -> TYPE: music" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.136, 0.418, 0.178] in the image\nAnd my action is Action: TYPE\nValue: ohio" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[div] Search for events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.057, 0.326, 0.09] in the image\nAnd my action is Action: TYPE\nValue: pet festival" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 job opening in sales in San Fransisco, and if found, apply for the job.\nPrevious actions:\n[link] Our Team -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.052, 0.179, 0.258, 0.2] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is [email protected], and phone number is 6157075521.\nPrevious actions:\n[link] Car Repair -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.716, 0.03, 0.88, 0.03] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the empire builder route in West US part of heartland and check the Minnesota stop.\nPrevious actions:\n[button] DESTINATIONS -> CLICK\n[polygon] -> CLICK\n[button] Heartland -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.415, 0.157, 0.423] 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 latest documentaries on Netflix and add the one with 70+ metascore.\nPrevious actions:\n[link] What to Watch on Netflix -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.396, 0.31, 0.408] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: BERLIN\n[span] Berlin -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.06, 0.327, 0.074] in the image\nAnd my action is Action: TYPE\nValue: ZURICH" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking near Sofi stadium that allows to pay with phone.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: sofi stadium\n[span] SoFi Stadium -> CLICK\n[strong] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.315, 0.379, 0.333] 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: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.325, 0.016, 0.461, 0.043] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to national parks -> CLICK\n[heading] Southeast Region -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.552, 0.884, 0.593] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request ticket receipt for ticket no. 1234567890123 and last name Davis\nPrevious actions:\n[link] Receipts and refunds -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.188, 0.252, 0.196] 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 Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] From Departure Airport or City Your Origin -> TYPE: Mumbai\n[link] BOM Mumbai, India -> CLICK\n[link] To Destination Airport or City Your Destination -> CLICK\n[textbox] Destination City or Airport -> TYPE: New York City\n[link] NYC New York City Area Airports, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.067, 0.46, 0.092] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a demo drive for Model Y for Roy Adams with phone number 123-999-0000, email address [email protected] and zip code 90001 in the United States.\nPrevious actions:\n[link] Demo Drive -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.679, 0.55, 0.841, 0.581] 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[button] 03/31/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK\n[button] Selected Pick-Up Date 03/31/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.662, 0.457, 0.834, 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: Get a rental car to pick up at Paris Charles de Gaulle Airport CDG on april 13 at 10 am and drop off on april 18 at the same time\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: Paris Charles de Gaulle Airport (CDG)\n[button] Paris Charles de Gaulle Airport (CDG) Paris, Franc... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.262, 0.171, 0.278] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[option] Manila Luzon, Philippines -> CLICK\n[svg] -> CLICK\n[gridcell] 1 June 2023 -> CLICK\n[gridcell] 8 June 2023 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.576, 0.263, 0.595] 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 rental charges for bikes in 37863.\nPrevious actions:\n[link] Find a Store -> CLICK\n[textbox] Enter ZIP or City, State -> TYPE: 37863" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.389, 0.159, 0.407, 0.169] 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 tickets as gifts and book 2 tickets for stand-up comedian Dave Chappelle and the roots shows.\nPrevious actions:\n[link] Tickets as Gifts – Best Tickets to Buy Online -> CLICK\n[link] Dave Chapelle -> CLICK\n[link] TICKETS -> CLICK\n[p] Any Quantity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.782, 0.209, 0.792, 0.218] 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: List pg-13 comedy movies currently in theatres with the highest audience scores\nPrevious actions:\n[link] MOVIES -> CLICK\n[svg] -> CLICK\n[select-label] Audience score (highest) -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.457, 0.326, 0.58, 0.342] 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: Use the FareFinder to find flights for $150 or less from Dublin to anywhere.\nPrevious actions:\n[button] Plan -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.215, 0.081, 0.27, 0.091] 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: Open community discussions for Dota 2 game and open latest topic.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.405, 0.0, 0.482, 0.033] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest cars available at San Francisco Airport for a day.\nPrevious actions:\n[link] San Francisco Airport -> CLICK\n[div] Fri, Mar 31 -> CLICK\n[checkbox] 29 March 2023 -> CLICK\n[div] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.667, 0.269, 0.927, 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 superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\n[checkbox] Based On Comic Book (226) -> CLICK\n[strong] IMDb Rating -> CLICK\n[group] IMDb user rating (average) -> SELECT: 7.0\n[group] IMDb user rating (average) -> SELECT: 9.0\n[strong] Refine -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.452, 0.127, 0.54, 0.137] in the image\nAnd my action is Action: SELECT\nValue: Number of Votes" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[textbox] From -> CLICK\n[button] Ireland -> CLICK\n[span] Dublin -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.17, 0.174, 0.286, 0.191] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search for SkyMiles domestic Award Deals from Philadelphia to Atlanta.\nPrevious actions:\n[tab] SkyMiles -> CLICK\n[link] SkyMiles Award Deals -> CLICK\n[combobox] Origin -> CLICK\n[option] PHL Philadelphia, PA -> CLICK\n[combobox] Destination -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.357, 0.349, 0.643, 0.366] 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 first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[textbox] From -> TYPE: san francisco\n[a] SFO - San Francisco International, CA -> CLICK\n[textbox] To -> TYPE: new york\n[a] NYC - New York, NY -> CLICK\n[combobox] Number of passengers -> SELECT: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.169, 0.365, 0.187] 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 and book the cheapest daytime only monthly parking option in Seattle near Stripe, 5th Avenue\nPrevious actions:\n[li] Stripe, 5th Avenue, Seattle, WA, USA -> CLICK\n[tab] Monthly -> CLICK\n[select] All Parking Options -> SELECT: Daytime Only Parking\n[select] Sort by Distance -> SELECT: Sort by Price\n[heading] 335 Columbia St. - MOTORCYCLE PARKING ONLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.642, 0.674, 0.819, 0.711] 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[link] Long-Term Car Rental -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: orlando\n[span] Orlando Intl Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.129, 0.697, 0.169] 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 premium car in Brooklyn for a day.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Rent A Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.142, 0.495, 0.166] in the image\nAnd my action is Action: TYPE\nValue: Brooklyn" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show camping hammocks with lowest price first.\nPrevious actions:\n[button] Camp & Hike -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.049, 0.128, 0.069] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request information for tickets for a group of 100 people at a park in california\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.051, 0.77, 0.075] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse round-trip bus tickets from Houston to Dallas leaving on May 7th and returning a week later.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Houston\n[span] Houston, TX -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Dallas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.22, 0.387, 0.232] 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 men's running shoes of size 9 with lowest price and add to bag.\nPrevious actions:\n[menuitem] Men -> CLICK\n[link] Shoes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.232, 0.115, 0.244] 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 today's deals on video games and find the best deal on the lowest-priced mouse.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Movies, Music & Games -> CLICK\n[link] Video Games -> CLICK\n[link] Today's Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.258, 0.05, 0.266] 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 musical instruments and filter the results to show only those that are available for free local pickup.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.03, 0.652, 0.053] 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 treehouse in India with free cancellation and below $100 per night.\nPrevious actions:\n[img] -> CLICK\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: India" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.175, 0.171, 0.438, 0.218] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest bus for 2 persons from New York to Washington, DC.\nPrevious actions:\n[label] One way -> CLICK\n[textbox] From (type text or use the arrow keys) -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.341, 0.148, 0.353] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[button] Tuesday, April 11, 2023 -> CLICK\n[button] Friday, April 14, 2023 -> CLICK\n[button] 1 Traveler -> CLICK\n[textbox] 1 Adults, 18 to 64 years old, 1 of 8 passengers se... -> TYPE: 1\n[combobox] undefined Selected 1 room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.813, 0.339, 0.836] 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: Open my item inventory.\nPrevious actions:\n[link] BUCKEYE.FOOBAR -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.151, 0.481, 0.167] 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 an event from the 2019 UFC schedule and show me the full profile from one of the athletes\nPrevious actions:\n[link] MMA -> HOVER\n[link] Schedule/Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.197, 0.091, 0.214] in the image\nAnd my action is Action: SELECT\nValue: 2019" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mens hiking shoes under $100 in size 10 that has biggest discount.\nPrevious actions:\n[link] $25 to $50 (18) -> CLICK\n[link] $50 to $100 (146) -> CLICK\n[div] Size -> CLICK\n[link] 10 (131) -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.466, 0.974, 0.491] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[label] Pick-up location -> TYPE: BANGKOK\n[div] Downtown Bangkok -> CLICK\n[div] Thu, Apr 20 -> CLICK\n[checkbox] 24 May 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.609, 0.222, 0.636, 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 the schedule for the Dallas Mavericks.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.028, 0.178, 0.046] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a smartwatch to the cart that is compatible with an iPhone.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: smartwatch" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.105, 0.673, 0.131] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[link] SSD Storage -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.268, 0.868, 0.28] 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 Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Flight status -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.381, 0.281, 0.389] 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[link] 24 -> CLICK\n[textbox] Sun Mar 26  -> CLICK\n[link] 27 -> CLICK\n[combobox]  -> SELECT: 1 Room\n[combobox]  -> SELECT: 2 Adults" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.556, 0.139, 0.646, 0.176] in the image\nAnd my action is Action: SELECT\nValue: 1 Child" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check all Bayern Munich goalie stats\nPrevious actions:\n[div] Soccer -> CLICK\n[div] Bundesliga -> CLICK\n[div] Bayern Munich -> CLICK\n[heading] STATS -> CLICK\n[link] GOALS Jamal Musiala Jamal Musiala 11 G -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.51, 0.159, 0.678, 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: Check the French best sellers under $40 available in digital that are currently in stock.\nPrevious actions:\n[link] Bestsellers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.324, 0.196, 0.354] in the image\nAnd my action is Action: SELECT\nValue: US$20 to US$40" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 alerts and conditions for the Alagnak Wild River.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.294, 0.539, 0.305] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of children's program events in Illinois.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.381, 0.321, 0.93, 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 tickets from Manchester Piccadilly to any station in London on April 8, leaving nearest 10 AM for 1 adult\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> CLICK\n[combobox] Departure station, none selected. Select a station... -> TYPE: Manchester\n[span] Manchester Piccadilly -> CLICK\n[span] London -> CLICK\n[textbox] Date use format: 16-Mar-23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.442, 0.174, 0.471, 0.189] 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 camping tents that can fit 6 people and sort the results by price from low to high.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[link] Camping Tents -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.238, 0.127, 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: Show camping hammocks with lowest price first.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[button] Camp & Hike -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.555, 0.194, 0.709, 0.204] 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 the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[div] -> CLICK\n[button] close -> CLICK\n[button] Pizza Crust Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.572, 0.237, 0.654] 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 all free virtual business start-up events happening tomorrow in Las Vegas and follow the organizer with most followers.\nPrevious actions:\n[link] Business -> CLICK\n[svg] -> CLICK\n[combobox] autocomplete -> TYPE: LAS VEGAS" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.176, 0.247, 0.209] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Prometheus movie to watchlist.\nPrevious actions:\n[textbox] Search IMDb -> CLICK\n[textbox] Search IMDb -> TYPE: Prometheus\n[div] Prometheus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.701, 0.316, 0.942, 0.354] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.093, 0.763, 0.137] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[button] Meetings & Events -> CLICK\n[link] Book An Event Book a Meeting or Event -> CLICK\n[textbox] Destination -> TYPE: Boston\n[menuitem] Boston, MA, USA -> CLICK\n[textbox] Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.61, 0.517, 0.648, 0.535] 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 the fare options to go from the south station to the north station\nPrevious actions:\n[button] Fares  -> CLICK\n[link] Fares Overview -> CLICK\n[combobox] Enter a location -> TYPE: south station\n[link] T red line silver line commuter rail Zone 1A Sout... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.675, 0.236, 0.845, 0.251] in the image\nAnd my action is Action: TYPE\nValue: north station" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the full menu for AMC Dine-In\nPrevious actions:\n[link] Visit the Food & Drinks page -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.285, 0.123, 0.488, 0.146] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\n[link] WOMEN -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.085, 0.257, 0.106] 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 and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[label] Medium Light -> CLICK\n[svg] -> CLICK\n[label] 32\" -> CLICK\n[svg] -> CLICK\n[label] Less than $100 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.79, 0.309, 0.955, 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: Show review of Prometheus movie.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.083, 0.033, 0.097] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\n[link] Home Services -> HOVER\n[span] Locksmiths -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.023, 0.564, 0.037] in the image\nAnd my action is Action: TYPE\nValue: SAN FRANSISCO" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[gridcell] 1 June 2023 -> CLICK\n[gridcell] 8 June 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[button] Show all 14 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.885, 0.263, 0.897] in the image\nAnd my action is Action: CLICK" } ]