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: 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[textbox] Search by Keyword -> TYPE: developer\n[textbox] Search by Location -> TYPE: dallas\n[button] Search Jobs -> CLICK\n[link] Developer/ Senior Developer, IT -> CLICK\n[spinbutton] Select how often (in days) to receive an alert: -> TYPE: 8" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.216, 0.463, 0.242] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[ins] -> CLICK\n[ins] -> CLICK\n[link] Show all 10 cars -> CLICK\n[link] Opel Insignia or Similar , View deal -> CLICK\n[radio] Radio yes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.832, 0.7, 0.93, 0.748] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: Paris\n[menuitem] Paris France CDG Charles De Gaulle Airport -> CLICK\n[option] One way -> CLICK\n[gridcell] 17 April 2023 -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.494, 0.94, 0.539] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[combobox] Pick Up Time -> SELECT: 9:00 AM\n[combobox] Return Time -> SELECT: 9:00 AM\n[button] Select My Car -> CLICK\n[link] Recommended -> CLICK\n[link] Price (Low to High) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.793, 0.374, 0.918, 0.392] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 laptops with at least 16gb of ram and under $700.\nPrevious actions:\n[searchbox] Search Site -> TYPE: laptop" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.496, 0.014, 0.546, 0.042] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.45, 0.271, 0.491] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[LabelText] Certified Pre-Owned -> CLICK\n[combobox] Select Make -> SELECT: Lexus\n[combobox] Select Model -> SELECT: RX" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.521, 0.192, 0.599, 0.218] in the image\nAnd my action is Action: TYPE\nValue: 90012" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[textbox] Start Date -> CLICK\n[button]  -> CLICK\n[gridcell] Tue, May 30, 2023 -> CLICK\n[gridcell] Thu, Jun 1, 2023 -> CLICK\n[label] Purpose of your event -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.664, 0.393, 0.958, 0.429] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.542, 0.114, 0.627, 0.152] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade-in value for Call of Duty: Black Ops III for Xbox One.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: trade in" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.061, 0.228, 0.083] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[button] Columbus, OH, US (CMH) -> CLICK\n[combobox] To -> TYPE: new orleans\n[button] New Orleans, LA, US (MSY) -> CLICK\n[textbox] Depart date -> CLICK\n[button] Sunday, April 9, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.408, 0.562, 0.452] in the image\nAnd my action is Action: SELECT\nValue: Business or First" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Birmingham, England, United Kingdom -> CLICK\n[textbox] Enter destination or airport -> TYPE: Paris\n[span] City -> CLICK\n[generic] Tuesday April 4th -> CLICK\n[div] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.391, 0.186, 0.424, 0.22] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Surname -> TYPE: Bloggs\n[textbox] Email address -> TYPE: [email protected]\n[textbox] Confirm email address -> TYPE: [email protected]\n[input] -> TYPE: 1111111111111111\n[textbox] Address 1 -> TYPE: the home of joe bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.683, 0.631, 0.716] 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: Show offers on home essentials under $20 and add the first 3 items to favorites.\nPrevious actions:\n[link] Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.151, 0.32, 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: Browse comedy TV shows streaming on HBO Max that was released in 2010.\nPrevious actions:\n[link] What to Watch on HBO Max -> CLICK\n[button] Filter -> CLICK\n[button] Comedy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.187, 0.295, 0.199] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the trending searches in Columbus.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.001, 0.417, 0.039] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[link] Flights -> CLICK\n[link] Search flights multiple cities -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: JFK\n[a] JFK - New York John F Kennedy Intl, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.389, 0.492, 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: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Model -> CLICK\n[listitem] Civic (35) Civic (35) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK\n[button] 2010 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.458, 0.238, 0.489] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 motorcycle parking near Radio City Music Hall.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: radio city music hall" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.444, 0.748, 0.47] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[combobox] To  -> TYPE: NORTH PLYMOUTH\n[em] Plymouth -> CLICK\n[button] Depart at 8:20 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 28, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.354, 0.195, 0.38] 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 musical instruments and filter the results to show only those that are available for free local pickup.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: musical instruments" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.174, 0.643, 0.193] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for used Jaguar XFs with no black exterior color and save the search as Jaguar to get a notification daily.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.033, 0.937, 0.053] in the image\nAnd my action is Action: TYPE\nValue: jaguar xf" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[checkbox] Engineering (41 items) -> CLICK\n[checkbox] Spain (18 items) -> CLICK\n[checkbox] Madrid (2 items) -> CLICK\n[link] Title: IT Support Engineer -> CLICK\n[textbox] First Name (as per passport) (required) -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.801, 0.493, 0.92, 0.514] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to popular destinations -> CLICK\n[textbox] Input departure airport -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.329, 0.485, 0.487, 0.496] in the image\nAnd my action is Action: TYPE\nValue: Honolulu" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[button] Add To Cart -> CLICK\n[link] Confirm Membership to Checkout -> CLICK\n[input] -> TYPE: Joe\n[input] -> TYPE: Bloggs\n[input] -> TYPE: 123456789" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.417, 0.216, 0.449] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 price of Boys' INFANT UA SURGE 3 RUNNING SHOES. black color and 9K size\nPrevious actions:\n[menuitem] Kids -> CLICK\n[div] Product Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.323, 0.194, 0.334] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[tab] Rail Passes -> CLICK\n[link] EXPLORE MULTI-RIDE PASSES -> CLICK\n[textbox] From -> TYPE: WASHINGTON" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.116, 0.278, 0.139] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[button] Let's go -> CLICK\n[link] Large cars 5 Seats 3 Large bags -> CLICK\n[ins] -> CLICK\n[ins] -> CLICK\n[ins] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.852, 0.348, 0.966, 0.402] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: Brooklyn\n[option] Brooklyn, NY, US Select -> CLICK\n[button] Selected Pick-Up Date 03/19/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.691, 0.691, 0.739] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[link] Book Meetings & Events -> CLICK\n[heading] Weddings -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Wedding -> CLICK\n[textbox] Destination -> TYPE: Venice Beach" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.237, 0.335, 0.256] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open community discussions for Dota 2 game and open latest topic.\nPrevious actions:\n[link] COMMUNITY -> HOVER\n[link] DISCUSSIONS -> CLICK\n[link] Game Forums -> CLICK\n[textbox] Search by game -> TYPE: Dota 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.408, 0.307, 0.992, 0.326] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.058, 0.174, 0.066] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Kitchen -> CLICK\n[link] Kitchen Sinks -> CLICK\n[link] Drop In Two Bowl -> CLICK\n[checkbox] Ship to Home Eligible (97) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.291, 0.116, 0.307] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Gift Cards  -> CLICK\n[link] Browse Gift Cards -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.243, 0.237, 0.31, 0.257] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[link] Hotels -> CLICK\n[searchbox] Type your destination -> TYPE: Las Vegas\n[option] Las Vegas Nevada, United States -> CLICK\n[checkbox] 10 April 2023 -> CLICK\n[gridcell] 16 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.82, 0.254, 0.927, 0.278] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all time popular drop c rock tab of beginner difficulty\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Beginner 554,088 -> CLICK\n[link] Drop C 3,930 -> CLICK\n[link] Rock 2,420 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.361, 0.291, 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: Show me FAQs related to eating and drinks\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.056, 0.286, 0.076] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check Manchester City Performance Stats of 2022/2023 season in the champions league\nPrevious actions:\n[link] ESPN Soccer Home Page -> HOVER\n[link] Champions League -> CLICK\n[link] Manchester City -> CLICK\n[link] Stats -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.229, 0.17, 0.251] in the image\nAnd my action is Action: SELECT\nValue: UEFA Champions League" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: BATMAN" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.062, 0.668, 0.075] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.404, 0.203, 0.421] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[link] SEARCH CARS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.199, 0.249, 0.23] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Begin booking a 14 day cruise from Los Angeles to Hawaii\nPrevious actions:\n[span] Sail To -> CLICK\n[button] Hawaii -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Los Angeles, CA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.27, 0.871, 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: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[link] United States Car Rental Locations -> CLICK\n[searchbox] Location (required) * Required Field -> TYPE: 02199\n[span] 02199 -> CLICK\n[button] Continue -> CLICK\n[button] All Location Details -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.162, 0.428, 0.268, 0.465] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find JetBlue press releases for the year 2020\nPrevious actions:\n[link] Press RoomExternal Link should open in a new windo... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.852, 0.302, 0.945, 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: Find a Thai restaurant and get notified when they have an open table between 5 to 7 PM\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.183, 0.027, 0.456, 0.061] in the image\nAnd my action is Action: TYPE\nValue: thai" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 blue iPad to your cart and select the option for free engraving with \"hello world\" with no other accessaries.\nPrevious actions:\n[link] iPad -> CLICK\n[link] Buy iPad 10.9-inch -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.375, 0.755, 0.392] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Flight status on 21 April for flight number DL145.\nPrevious actions:\n[tab] FLIGHT STATUS -> CLICK\n[span] Mon, Apr 10 -> CLICK\n[link] 21 April 2023, Friday -> CLICK\n[button] done -> CLICK\n[spinbutton] Flight Number (Required) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.109, 0.562, 0.148] in the image\nAnd my action is Action: TYPE\nValue: DL145" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movies in theaters that are certified fresh and sorty by highest audience score.\nPrevious actions:\n[link] MOVIES -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.304, 0.716, 0.318] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 WWE ticket for price range between $50 to $100.\nPrevious actions:\n[link] WWE Tickets -> CLICK\n[link] TICKETS -> CLICK\n[p] $41 - $1,255 -> CLICK\n[input] -> TYPE: 50" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.207, 0.837, 0.231] in the image\nAnd my action is Action: TYPE\nValue: 100" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: street taco\n[li] Street Taco, Broadway, New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.306, 0.195, 0.317] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comprehensive health screening for women in 10003.\nPrevious actions:\n[span] Schedule a women's health exam -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.395, 0.578, 0.605, 0.62] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.053, 0.267, 0.075] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox One -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.205, 0.094, 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: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[link] Careers  -> CLICK\n[link] Students & Grads -> CLICK\n[link] INTERNSHIP PROGRAMS -> CLICK\n[link] HOTEL INTERNSHIPS INTERNATIONAL -> CLICK\n[button] Locations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.384, 0.166, 0.446, 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 a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[link] Collectibles -> CLICK\n[button] Antiques -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.255, 0.184, 0.273] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the user reviews for the game \"Cyberpunk 2077\"\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Search -> TYPE: Cyberpunk 2077" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.221, 0.677, 0.283] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight status for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\n[generic] Apr 7, 2023 -> CLICK\n[option] Apr 9, 2023 -> CLICK\n[combobox] Airline. Enter to change collapsed list. Selected ... -> CLICK\n[option] United Airlines (UA) -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: belo horizonte" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.102, 0.312, 0.342, 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[link] SEARCH CARS -> CLICK\n[div] Best match -> CLICK\n[label] Nearest distance -> CLICK\n[button] Back to all categories -> CLICK\n[button] Distance & Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.312, 0.237, 0.325] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[link] hotels. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.186, 0.247, 0.288, 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: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[button] Continue with this address -> CLICK\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK\n[button] Continue -> CLICK\n[textbox] Credit card number -> TYPE: 123456789" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.474, 0.302, 0.496] in the image\nAnd my action is Action: TYPE\nValue: 01" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight from Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] BOM Mumbai, India -> CLICK\n[link] To Destination Airport or City Your Destination -> CLICK\n[textbox] Destination City or Airport -> TYPE: New York City\n[link] NYC New York City Area Airports, NY -> CLICK\n[combobox] Trip Type:, changes will reload the page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.118, 0.46, 0.141] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[span] Faro -> CLICK\n[textbox] To -> TYPE: bournemouth" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.199, 0.715, 0.214] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.07, 0.777, 0.085] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[searchbox] From -> TYPE: grand central\n[span] Grand Central -> CLICK\n[searchbox] To -> CLICK\n[div] Recent Stations -> CLICK\n[searchbox] To -> TYPE: stoney brook" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.43, 0.474, 0.463] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals for Hotels in Mexico.\nPrevious actions:\n[textbox] What type of deals? -> TYPE: Hotels\n[div] Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.303, 0.136, 0.492, 0.195] in the image\nAnd my action is Action: TYPE\nValue: Mexico" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[link] Business Meetings  -> CLICK\n[textbox] Destination -> TYPE: new delhi\n[menuitem] New Delhi, Delhi, India -> CLICK\n[textbox] Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.605, 0.18, 0.648, 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: Find a multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] 43229 -> TYPE: 44240\n[button] UPDATE -> CLICK\n[checkbox] Pickup at Store Eligible (86) -> CLICK\n[checkbox] Multi-Purpose Tool (11) -> CLICK\n[checkbox] Red Devil (2) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.377, 0.552, 0.388] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[path] -> CLICK\n[link] View More -> CLICK\n[img] -> CLICK\n[span] Add to list -> CLICK\n[checkbox] Walgreens New -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.838, 0.691, 0.873] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Delete the history of what i heard recently.\nPrevious actions:\n[link] Library -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.57, 0.046, 0.634, 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 value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[button] Go -> CLICK\n[div] XLE Sedan 4D -> CLICK\n[button] Next -> CLICK\n[div] Select Your Options -> CLICK\n[generic] Black image Black -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.202, 0.634, 0.242] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: bali\n[generic] Indonesia -> CLICK\n[gridcell] Sat Apr 01 2023 -> CLICK\n[button] 4 -> CLICK\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.256, 0.393, 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: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] Next -> CLICK\n[span] -> CLICK\n[div] Leather -> CLICK\n[button] Next -> CLICK\n[button] None -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.554, 0.286, 0.591] in the image\nAnd my action is Action: SELECT\nValue: Good" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Paint -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.365, 0.222, 0.524, 0.252] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[span] Hollywood -> CLICK\n[button] 19 -> CLICK\n[button] 23 -> CLICK\n[img] Add -> CLICK\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.214, 0.808, 0.241] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the weekly ad in List View.\nPrevious actions:\n[button] Savings & Memberships -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.132, 0.638, 0.154] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find men's running shoes of size 9 with lowest price and add to bag.\nPrevious actions:\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\n[button] 9 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.664, 0.795, 0.952, 0.833] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find artist Mark Knight from London and follow him and add his most liked track to next up.\nPrevious actions:\n[searchbox] Search -> TYPE: Mark Knight\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.372, 0.092, 0.441, 0.101] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[link] Car Values -> HOVER\n[link] My Car's Value -> CLICK\n[div] Make/Model -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.204, 0.192, 0.227] in the image\nAnd my action is Action: SELECT\nValue: 2016" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Remove the SSD on my cart\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.903, 0.014, 0.984, 0.045] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] CITIES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.617, 0.349, 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 superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\n[checkbox] Superhero Sci Fi (745) -> CLICK\n[checkbox] Based On Comic Book (226) -> CLICK\n[strong] IMDb Rating -> CLICK\n[group] IMDb user rating (average) -> SELECT: 7.0\n[group] IMDb user rating (average) -> SELECT: 9.0" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.15, 0.224, 0.182, 0.232] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[region] 4 Stars & Up -> CLICK\n[link] $50 to $100 -> CLICK\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK\n[link] Amazon Basics 7-Piece Lightweight Microfiber Bed-i... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.702, 0.49, 0.765, 0.565] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find JetBlue career openings in New York\nPrevious actions:\n[link] CareersExternal Link should open in a new window o... -> CLICK\n[textbox] Search by Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.406, 0.261, 0.688, 0.281] 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 an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[button] Discover -> CLICK\n[link] Upcoming Games -> CLICK\n[combobox] Platform -> SELECT: PS5" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.058, 0.737, 0.075] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the parking options in Florida to book to enter on may 6 at 5 pm and leave the same day at 6pm?\nPrevious actions:\n[li] Florida, USA -> CLICK\n[textbox] Start Date -> CLICK\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK\n[combobox] Start Time -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.301, 0.384, 0.338] in the image\nAnd my action is Action: SELECT\nValue: 6 00 PM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\n[span] View all 20+ items -> CLICK\n[span] Best match -> CLICK\n[option] Price: lowest first -> CLICK\n[span] Add -> CLICK\n[span] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.477, 0.856, 0.727, 0.9] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking button code for my company Boston Legal located near Boston Navy Yard, and the button should be 160x400 pixels, and the parking spot should be within 15 miles of my address.\nPrevious actions:\n[link] ADD PARKING TO YOUR WEBSITE -> CLICK\n[textbox] STEP 1: Enter Your Company Name -> TYPE: BOSTON LEGAL" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.163, 0.457, 0.486, 0.483] in the image\nAnd my action is Action: TYPE\nValue: BOSTON NAVY YARD" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.064, 0.546, 0.102] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule COVID-19 test appointment at 90028.\nPrevious actions:\n[span] COVID-19 booster, testing, treatment & records -> CLICK\n[link] COVID-19 testing Schedule a COVID-19 test -> CLICK\n[textbox] Where do you live? (required) -> TYPE: 90028" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.633, 0.266, 0.844, 0.287] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[link] Careers -> CLICK\n[link] Open Jobs -> CLICK\n[span] -> CLICK\n[button] Country -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.313, 0.245, 0.358] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[link] Shop -> CLICK\n[img] Sports car icon -> CLICK\n[button] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.289, 0.243, 0.296] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[heading] CAR -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.843, 0.481, 0.856] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for 2 guests on april 21 at noon in a restaurant in Austin that is new on resy\nPrevious actions:\n[path] -> CLICK\n[button] Austin -> CLICK\n[heading] New On Resy -> CLICK\n[button] Sat., Apr. 22 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.169, 0.35, 0.184] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the safety rating for 2012 Honda Civic\nPrevious actions:\n[generic] Your Opinion Counts! -> CLICK\n[img] Close -> CLICK\n[combobox] Make -> SELECT: Honda\n[combobox] Model -> SELECT: Civic\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.568, 0.482, 0.621, 0.526] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me things to do nearby in Mar 30, 202\n3\nPrevious actions:\n[textbox] Where to? -> CLICK\n[button] Nearby -> CLICK\n[gridcell] Thu Mar 30 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.45, 0.78, 0.477] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\n[link] Hip-hop & Rap -> CLICK\n[div] Play -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[a] Create a playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.083, 0.695, 0.095] in the image\nAnd my action is Action: TYPE\nValue: Top Hip Hop" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: albany\n[span] Albany, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.14, 0.797, 0.161] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.252, 0.318, 0.285] in the image\nAnd my action is Action: TYPE\nValue: albany" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[textbox] Departure -> CLICK\n[button] Tuesday, April 11, 2023 -> CLICK\n[button] Friday, April 14, 2023 -> CLICK\n[button] 1 Traveler -> CLICK\n[textbox] 1 Adults, 18 to 64 years old, 1 of 8 passengers se... -> TYPE: 1" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.828, 0.34, 0.861] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.044, 0.644, 0.066] in the image\nAnd my action is Action: TYPE\nValue: iPhone 12 Pro" } ]