Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 84

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Lenovo laptop under $800 and create a price alert for $400.\nPrevious actions:\n[searchbox] Search Site -> TYPE: lenovo laptop\n[button]  -> CLICK\n[div] Newest Lenovo Ideapad 3i Laptop, 14\" FHD Display, ... -> CLICK\n[div] Price Alert -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.217, 0.495, 0.231] in the image\nAnd my action is Action: TYPE\nValue: 400" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the next available bus from Chicago to Ann Arbor.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Chicago\n[span] Chicago, IL -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Ann Arbor\n[span] Ann Arbor, MI -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.323, 0.831, 0.34] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the trade-in options for PS4.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.697, 0.048, 0.722, 0.062] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade in value for PS4 console\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Consoles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.284, 0.932, 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: Book me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: BWI\n[button] Baltimore, MD, US (BWI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: NYC" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.356, 0.582, 0.394] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.129, 0.364, 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: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[button] VIEW ALL -> CLICK\n[img] -> CLICK\n[textbox] To: -> TYPE: John\n[textbox] From: -> TYPE: James\n[textbox] Message: 200 characters remaining -> TYPE: Congrats on your new home." }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.658, 0.57, 0.789, 0.591] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] From -> CLICK\n[searchbox] From -> TYPE: empire state building\n[listitem] Empire State Building, West 34th Street, New York,... -> CLICK\n[searchbox] To -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.182, 0.359, 0.199] in the image\nAnd my action is Action: TYPE\nValue: little caribbean" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[link] Gifting -> CLICK\n[link] Gift Cards -> CLICK\n[div] Send a physical card through the mail. -> CLICK\n[textbox] * Amount: -> TYPE: 50" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.866, 0.134, 0.956, 0.17] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.591, 0.021, 0.645, 0.055] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.244, 0.568, 0.264] in the image\nAnd my action is Action: TYPE\nValue: Dallas" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 showtimes for John Wick 4 at a theater in Wichita, Kansas 67226\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK\n[link] Find a Theatre -> CLICK\n[link] Wichita -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.334, 0.14, 0.346] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Route map -> CLICK\n[textbox] Pick an origin Pick a destination -> TYPE: Abbotsford\n[span] Abbotsford, WI -> CLICK\n[textbox] Enter a town, city or zipcode -> TYPE: Sheboygan" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.366, 0.168, 0.381] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated mover in Honolulu to shift a vehicle and large appliances out of state and who has virtual discussion options available.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.158, 0.02, 0.243, 0.036] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a large store in Washington that has kids' and maternity products, also check if they have a parking lot, and see the directions of the nearest store.\nPrevious actions:\n[link] Store Locator -> CLICK\n[input] -> CLICK\n[option] WA -> CLICK\n[button] Products -> CLICK\n[label] Kids -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.653, 0.412, 0.666] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] Card number -> TYPE: 1234\n[combobox] Card type -> SELECT: MasterCard\n[combobox] Month -> SELECT: 01\n[combobox] Year -> SELECT: 2023\n[textbox] CVV -> TYPE: 123" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.233, 0.95, 0.285] in the image\nAnd my action is Action: TYPE\nValue: joe bloggs" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\n[div] hotels -> CLICK\n[textbox] Destination or property -> TYPE: Athens, Attica, Greeece\n[div] , Greece -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.181, 0.273, 0.227] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[div] 7 -> CLICK\n[button] Tuesday April 11, 2023 -> CLICK\n[svg] -> CLICK\n[checkbox] Free internet -> CLICK\n[button] Amenities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.721, 0.089, 0.727] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Museums in New York City.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.006, 0.348, 0.017] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[button] Last-Minute -> CLICK\n[button] $ Price: Low to High -> CLICK\n[button] DONE -> CLICK\n[heading] $139 Vermont: Cozy Kimpton in the heart of Manches... -> CLICK\n[button] CHECK DATES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.701, 0.061, 0.74, 0.081] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check all English Reading and Writing skills Educational Books for Ages 6-8 currently in stock that are available in hardback under 20$.\nPrevious actions:\n[link] Shop by category∨ -> CLICK\n[link] Shop by category∨ -> CLICK\n[link] Ages 6-8 -> CLICK\n[link] Education -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.149, 0.196, 0.162] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant that offers African Cuisine in east village under $30\nPrevious actions:\n[link] restaurants. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.395, 0.275, 0.644, 0.304] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[path] -> CLICK\n[textbox] From -> TYPE: faro" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.274, 0.715, 0.299] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Airport information of Camarillo Airport, CA and check weather.\nPrevious actions:\n[combobox] Search Method -> SELECT: Airport\n[textbox] Airport City (e.g. New York) -> TYPE: Camarillo\n[strong] Camarillo -> CLICK\n[img] Submit Search -> CLICK\n[link] View KCMA Airport Stats -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.112, 0.353, 0.134] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\n[textbox] Enter zip code or location. Please enter a valid l... -> TYPE: 90028\n[img] -> CLICK\n[generic] 6201 Hollywood Blvd., Suite 126 -> CLICK\n[button] In Stock at 6201 Hollywood Blvd., Suite 126. 0.2 m... -> CLICK\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.672, 0.318, 0.812, 0.347] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Destination -> CLICK\n[option] ATL Atlanta, GA -> CLICK\n[button] Filters -> CLICK\n[combobox] Select Region Type -> CLICK\n[option] Domestic & North America -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.208, 0.565, 0.243] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new address to the account. The address is 2983 Marietta Street, APT 2. Business name is Buck.\nPrevious actions:\n[span] 171 2nd street -> CLICK\n[textbox] Add a new address -> TYPE: 2983 Marietta Street\n[span] 2983 Marietta Street -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.424, 0.702, 0.472] in the image\nAnd my action is Action: TYPE\nValue: 2" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vintage clothing and sort the results by price from high to low.\nPrevious actions:\n[combobox] Search for anything -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.048, 0.652, 0.071] in the image\nAnd my action is Action: TYPE\nValue: vintage clothing" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.187, 0.139, 0.212] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Size -> CLICK\n[link] 9 -> CLICK\n[span] Now Trending -> CLICK\n[li] Price (Low - High) -> CLICK\n[img] Men's UA Surge 3 Running Shoes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.867, 0.136, 0.924, 0.151] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me routes from NYP to WAS on May 15th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.154, 0.271, 0.173] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[button] COLUMBUS, OH -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.186, 0.294, 0.216] in the image\nAnd my action is Action: TYPE\nValue: 60538" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a list of available opportunities for a volunteer event for year 2023\nPrevious actions:\n[button] Open Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.093, 0.723, 0.108] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the photo gallery for Tsiakkos & Charcoal.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: Tsiakkos & Charcoal\n[heading] Tsiakkos & Charcoal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.893, 0.292, 0.977, 0.309] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Real Madrid team schedule of the UEFA Champions League championship.\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Real Madrid" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.189, 0.931, 0.226] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Begin booking a 14 day cruise from Los Angeles to Hawaii\nPrevious actions:\n[button] Hawaii -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Los Angeles, CA -> CLICK\n[button] SEARCH CRUISES -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.269, 0.173, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the balance for a gift card with the number 1000000000000000 and pin 1222\nPrevious actions:\n[link] Visit the Gift Cards page -> CLICK\n[link] Check Balance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.233, 0.5, 0.262] in the image\nAnd my action is Action: TYPE\nValue: 1000000000000000" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\n[combobox] Search for anything -> TYPE: laptop\n[button] Search -> CLICK\n[input] -> CLICK\n[textbox] Minimum Value in $ -> TYPE: 400" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.566, 0.147, 0.579] in the image\nAnd my action is Action: TYPE\nValue: 500" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[combobox] Time -> SELECT: 8:15 PM\n[combobox] Size -> SELECT: 10 guests\n[button] Update search -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Pizza -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.714, 0.628, 0.795, 0.672] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[textbox] $$$ -> TYPE: 10\n[button] close -> CLICK\n[button] Color -> 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 [0.828, 0.166, 0.898, 0.186] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights from Chicago to London on 20 April and return on 23 April.\nPrevious actions:\n[textbox] From -> TYPE: Chicago\n[a] CHI - Chicago, IL -> CLICK\n[textbox] To -> TYPE: London\n[a] LON - London, United Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.344, 0.197, 0.358, 0.213] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find jobs available in Texas for American Airlines.\nPrevious actions:\n[link] We're hiring! Join our team , Opens another site i... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.562, 0.618, 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: Find men's running shoes of size 9 with lowest price and add to bag.\nPrevious actions:\n[menuitem] Men -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.386, 0.106, 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: Check reviews and research information about Audi A6 2020.\nPrevious actions:\n[menuitem] Research -> CLICK\n[combobox] Select Make -> SELECT: Audi\n[combobox] Select Model -> SELECT: A6\n[combobox] Select Year -> SELECT: 2020\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.245, 0.301, 0.268] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[div] Mexico -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] May -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.277, 0.3, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces in JFK airport between April 18-20 that have lowest shuttle times\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.077, 0.563, 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: Search for developer jobs in Dallas, Texas, and review details of the latest job then create an 8-day alert after signing in.\nPrevious actions:\n[link] We're hiring! Join our team , Opens another site i... -> CLICK\n[button] Careers -> CLICK\n[link] View All Jobs -> CLICK\n[textbox] Search by Keyword -> TYPE: developer" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.439, 0.112, 0.766, 0.131] in the image\nAnd my action is Action: TYPE\nValue: dallas" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: BRISTOL\n[span] Bristol Airport (By Bus) -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: LONDON" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.234, 0.326, 0.267] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 campground in Phoenix with wi-fi to check in today.\nPrevious actions:\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: Phoenix" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.103, 0.547, 0.118] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the profile page for author of latest shot\nPrevious actions:\n[link] Shots -> CLICK\n[button] New -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.77, 0.149, 0.852, 0.165] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show events in Los Angeles and select the one on the Friday this weekend.\nPrevious actions:\n[button] CITY GUIDES -> HOVER\n[link] Los Angeles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.782, 0.195, 0.804, 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: 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[link] Discover -> CLICK\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: doha\n[strong] Doha -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 28 May 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.825, 0.346, 0.93, 0.365] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Edinburgh Waverly to Glagsgow Central on May 18, leaving nearest 3PM for 1 adult with a Veterans Railcard\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.064, 0.327, 0.084] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 exercise events taking place in San Francisco between July 10-31.\nPrevious actions:\n[link] Sports & Fitness -> CLICK\n[svg] -> CLICK\n[combobox] autocomplete -> TYPE: San Francisco" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.198, 0.247, 0.227] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.128, 0.064, 0.206, 0.12] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Next -> CLICK\n[input] -> TYPE: Crew\n[input] -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.532, 0.121, 0.777, 0.145] in the image\nAnd my action is Action: TYPE\nValue: Johnson" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 between New York and Washington DC sorted by shortest trip.\nPrevious actions:\n[textbox] From -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.226, 0.278, 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 kinect camera for xbox one.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.078, 0.646, 0.105] in the image\nAnd my action is Action: TYPE\nValue: kinect camera" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[link] Openings -> CLICK\n[button] Country -> CLICK\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK\n[button] Team -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.409, 0.307, 0.418] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the tables at Chianti - MG Road restaurant on March 30,1:30 PM for 4 Guests.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: CHIANTI\n[combobox] Guests -> SELECT: 4 Guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.199, 0.215, 0.219] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[span] Boston -> CLICK\n[button] Get trip suggestions -> CLICK\n[button] Depart at 8:40 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 14, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.315, 0.195, 0.338] in the image\nAnd my action is Action: TYPE\nValue: 12" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[div] Mr -> CLICK\n[textbox] First name -> TYPE: Joe\n[textbox] Last name -> TYPE: Bloggs\n[button] Continue -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.373, 0.27, 0.627, 0.288] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Add to playlist -> CLICK\n[button] Close -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[button] Add to playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.218, 0.712, 0.228] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.158, 0.024, 0.243, 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: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Build Your Own Custom PC Build Your Own Cu... -> CLICK\n[link]  CPU -> CLICK\n[button] START A NEW BUILD -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.667, 0.512, 0.692] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[combobox] To  -> TYPE: boston\n[span] Boston -> CLICK\n[button] Get trip suggestions -> CLICK\n[button] Depart at 8:40 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.296, 0.425, 0.323, 0.453] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Tree stands with at least 3 stars, and sort the results by price from low to high.\nPrevious actions:\n[link] Hunting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.173, 0.397, 0.183] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the women cropped tops with lowest price first.\nPrevious actions:\n[link] WOMEN -> CLICK\n[link] Cropped Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.891, 0.099, 0.959, 0.118] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse mens Timberland boots in size 9 and under $100 and filter by lowest price.\nPrevious actions:\n[button] Search -> CLICK\n[link] 9 - apply US Shoe Size filter -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 100\n[button] Submit price range -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.149, 0.905, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 set of sonoma bath towels to the cart and apply a coupon code for free shipping.\nPrevious actions:\n[img] Sonoma Goods For Life® Ultimate Bath Towel with Hy... -> CLICK\n[link] BATH TOWEL -> CLICK\n[button] Add to Cart -> CLICK\n[button] View Cart & Checkout -> CLICK\n[textbox] Add Kohl's Cash or Coupons -> TYPE: FREESHIP3093" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.46, 0.541, 0.529, 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 highest rated adventure game available for early access.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.071, 0.387, 0.078] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Activities  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.211, 0.695, 0.246] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule of the East Boston ferry, check connections, and fares and download the pdf schedule.\nPrevious actions:\n[button] Transit  -> CLICK\n[link] Ferry -> CLICK\n[span] East Boston Ferry -> CLICK\n[link] Schedule & Maps -> CLICK\n[button] Connections  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.641, 0.292, 0.875, 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: Search for hiking boots and filter the results to show only those with a waterproof rating of at least 3 stars.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[link] Hiking Footwear -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.597, 0.142, 0.61] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in Le maraise neighborhood in paris with 2 room for 3 adult on March 27th to April 2nd.\nPrevious actions:\n[div] 2 -> CLICK\n[button] Search -> CLICK\n[button] Number of rooms and guests -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.814, 0.042, 0.899, 0.071] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[link] Nearby Restaurants -> CLICK\n[div] Toronto -> CLICK\n[button] Chicago -> CLICK\n[button] Today -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.336, 0.318, 0.367] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Next Month -> CLICK\n[span] 11 -> CLICK\n[span] 18 -> CLICK\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.414, 0.267, 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: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[button] 15 -> CLICK\n[combobox] Time -> SELECT: 10:00 AM\n[combobox] Party size -> SELECT: 4 guests\n[svg] -> CLICK\n[button] Edit cuisine type filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.714, 0.264, 0.733, 0.289] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox Series X|S -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.198, 0.375, 0.231] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for Pizza making class in New York next month.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.123, 0.734, 0.165] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[i] -> CLICK\n[i] -> CLICK\n[span] SEARCH -> CLICK\n[tab] Lowest price first -> CLICK\n[checkbox] list-filter-item-label-0 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.832, 0.089, 0.842] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: JFK\n[span] New York -> CLICK\n[button] Selected Pick-Up Date 03/22/2023 -> CLICK\n[button] 03/27/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.239, 0.376, 0.261] in the image\nAnd my action is Action: SELECT\nValue: 11 00 AM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.441, 0.104, 0.581, 0.133] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] mm/dd/yyyy -> CLICK\n[select] June 2023 -> SELECT: June 2023\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 1:00 PM\n[button] Select My Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.757, 0.329, 0.882, 0.347] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\n[span] Attractions -> CLICK\n[searchbox] Where are you going? -> TYPE: Aquarium of Paris" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.304, 0.566, 0.34] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[link] Search for packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.141, 0.397, 0.175] in the image\nAnd my action is Action: TYPE\nValue: Birmingham" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest action tv shows which are rated fresh by both the audience and the rotten tomatoes\nPrevious actions:\n[button] APPLY -> CLICK\n[span] Audience score -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[span] Tomatometer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.773, 0.463, 0.794, 0.484] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the Recommended Gaming PCs for someone who plays Fortnite, Overwatch and GTA V at 4k\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK\n[div] Remove -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.196, 0.45, 0.304, 0.46] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spaces near Warner Theatre in Washington DC.\nPrevious actions:\n[link] CITIES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.521, 0.349, 0.536] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Renew a existing KOA rewards account with the rewards number 1000000001 e postal code 10023\nPrevious actions:\n[link] REWARDS PROGRAM -> CLICK\n[link] PURCHASE OR RENEW NOW  -> CLICK\n[radio] RENEW - An Existing Account -> CLICK\n[textbox] KOA Rewards Number -> TYPE: 1000000001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.431, 0.926, 0.466] in the image\nAnd my action is Action: TYPE\nValue: 10023" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Start the process to sign up for CVS ExtraCare\nPrevious actions:\n[button] Prescriptions -> CLICK\n[link] Pharmacy & Health Rewards -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.162, 0.418, 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: Show latest documentaries on Netflix and add the one with 70+ metascore.\nPrevious actions:\n[link] What to Watch on Netflix -> CLICK\n[button] Filter -> CLICK\n[button] Documentary -> CLICK\n[button] Release Date -> CLICK\n[button] View Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.826, 0.466, 0.845] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.664, 0.72, 0.909, 0.729] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[button] Kitchenware & tableware -> CLICK\n[link] Flatware & cutlery -> CLICK\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: san diego\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.863, 0.174, 0.981, 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: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[img] james9091 -> CLICK\n[link] Playlists -> CLICK\n[link] NEW PLAYLIST -> CLICK\n[button] START FROM SCRATCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.351, 0.241, 0.613, 0.286] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an English language book on roman empire history in the Kindle store released in the last 90 days, it should be displayed according to its latest publication date, and add the top result to the shopping list.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Kindle E-readers & Books -> CLICK\n[link] Kindle Books -> CLICK\n[textbox] Search Amazon -> TYPE: roman empire history" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.651, 0.007, 0.686, 0.035] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[button] Marketplace -> CLICK\n[link] Pop Rock -> CLICK\n[link] 958,222 United Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.298, 0.163, 0.311] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bike service charges for store at Lafayette St, 10013.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.081, 0.233, 0.114] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check reviews for best electric SUV and find the 1 star rated review and mark it helpful.\nPrevious actions:\n[link] Car Reviews -> HOVER\n[link] Best Cars -> CLICK\n[img] Best SUVs image -> CLICK\n[div] SUVs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.26, 0.71, 0.275] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive ticket for New York Knicks game on April 9\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.201, 0.782, 0.239] in the image\nAnd my action is Action: CLICK" } ]