Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add games with the title Atlantis to my collection.\nPrevious actions:\n[combobox] Search -> TYPE: Atlantis\n[svg] -> CLICK\n[link] Atlantis -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.237, 0.509, 0.249] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 detailed uses of Anuall Pass for 2023 on the USGS Online\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Passes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.472, 0.653, 0.547, 0.669] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\n[path] -> CLICK\n[switch] COMPARE -> CLICK\n[button] Add to Compare -> CLICK\n[button] Add to Compare -> CLICK\n[button] Go button to Compare the Selected Car's -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.323, 0.17, 0.336] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 is the purchase price for powerwalls to install in a 200sqr feet 2 story house in the address 7528 East Mechanic Ave.Fargo, ND 58102\nPrevious actions:\n[link] Powerwall -> CLICK\n[link] Order Now -> CLICK\n[textbox] Shipping Address -> TYPE: 7528 East Mechanic Ave. Fargo, ND 58102" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.722, 0.254, 0.919, 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 comedy tv shows on netflix sorted by audience score.\nPrevious actions:\n[link] TV SHOWS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.202, 0.252, 0.208] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[listitem] Chevrolet (101) Chevrolet (101) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Price -> CLICK\n[button] $10,000 -> CLICK\n[menuitem] $20,000 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.13, 0.325, 0.236, 0.35] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[span] -> CLICK\n[span] Search flights -> CLICK\n[link] Sort & Filter -> CLICK\n[button] Default   -> CLICK\n[span] Price (low to high) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.452, 0.817, 0.464] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Build Your Own Custom PC Build Your Own Cu... -> CLICK\n[link]  CPU -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.606, 0.578, 0.727, 0.594] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Comprehensive health screening Available in-person -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> TYPE: 10003\n[button] Find care -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.385, 0.571, 0.448, 0.603] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Reserve Now -> CLICK\n[link] Beverly Hills -> CLICK\n[button] Selected Pick-Up Date 03/21/2023 -> CLICK\n[button] 03/31/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.408, 0.449, 0.514, 0.486] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate vehicle price with a challenge credit score, monthly payment of $250 with a $3000 down payment and 24% APR for 48 months in Tennessee.\nPrevious actions:\n[link] Car payment calculator -> CLICK\n[tab] Vehicle Price -> CLICK\n[textbox] Monthly Payment -> TYPE: 250\n[textbox] Down Payment -> TYPE: 3000\n[combobox] State -> SELECT: Tennessee" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.266, 0.459, 0.288] in the image\nAnd my action is Action: SELECT\nValue: Challenged (< 580 FICO® Score)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a blue iPad to your cart and select the option for free engraving with \"hello world\" with no other accessaries.\nPrevious actions:\n[span] No Apple Pencil -> CLICK\n[span] No USB-C to Apple Pencil Adapter -> CLICK\n[span] No keyboard -> CLICK\n[span] No trade-in -> CLICK\n[span] Buy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.398, 0.938, 0.433] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights from New York City to London and filter the results to show only non-stop flights.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.087, 0.292, 0.107] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[link] Beverage Packages -> CLICK\n[img] -> CLICK\n[link] Beverage Packages -> CLICK\n[button] add Bottomless Bubbles to the cart with price $9.5... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.079, 0.447, 0.633, 0.527] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated mover in Honolulu to shift a vehicle and large appliances out of state and who has virtual discussion options available.\nPrevious actions:\n[checkbox] Vehicle -> CLICK\n[checkbox] Large appliances -> CLICK\n[radio] Out-of-state -> CLICK\n[button] Virtual Consultations -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.518, 0.166, 0.612, 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: check the most popular Spanish recipe book available in paperback that are in stock.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: recipe\n[link] recipe book -> CLICK\n[select] All -> SELECT: In Stock (7,640)\n[select] All -> SELECT: Spanish (42)\n[select] All -> SELECT: Paperback (39,356)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.313, 0.196, 0.335] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most reviewed cocktail bar with outdoor seating for reservation in San Francisco.\nPrevious actions:\n[link] Restaurants -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.219, 0.083, 0.329, 0.105] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.106, 0.424, 0.118] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[link] Categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.105, 0.316, 0.117] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[textbox] From -> TYPE: new york\n[strong] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.328, 0.174, 0.506, 0.204] in the image\nAnd my action is Action: TYPE\nValue: miami" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular free online fashion class events occurring this weekend in English, find details of the top result event, save the event and follow the organizer of this event.\nPrevious actions:\n[label] -> CLICK\n[label] -> CLICK\n[label] -> CLICK\n[svg] -> CLICK\n[div] RawElegant.Life -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.152, 0.556, 0.164] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[link] Products -> CLICK\n[button] Kitchenware & tableware -> CLICK\n[link] Flatware & cutlery -> CLICK\n[span] Columbus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.664, 0.067, 0.961, 0.09] in the image\nAnd my action is Action: TYPE\nValue: san diego" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.322, 0.233, 0.355] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[searchbox] Search -> TYPE: Selena Gomez\n[button] Search -> CLICK\n[link] Selena Gomez -> CLICK\n[link] Popular tracks -> CLICK\n[button] More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.408, 0.171, 0.518, 0.189] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a treehouse in India with free cancellation and below $100 per night.\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: India \n[div] India -> CLICK\n[span] -> CLICK\n[button] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.219, 0.739, 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: Book me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[button] Baltimore, MD, US (BWI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: NYC\n[button] New York, NY, US (NYC - All Airports) -> CLICK\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.249, 0.571, 0.261] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK\n[textbox] Where? -> TYPE: mexico" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.281, 0.89, 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: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[img] -> CLICK\n[link] Produce -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.335, 0.193, 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: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[button] Next -> CLICK\n[button] None -> CLICK\n[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.302, 0.284, 0.344] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[button] Book -> CLICK\n[link] Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.237, 0.397, 0.27] in the image\nAnd my action is Action: TYPE\nValue: washington" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 4 star rated Hotel in New York Timesquare for 2 adults.\nPrevious actions:\n[svg] -> CLICK\n[button] Done -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.476, 0.241, 0.795, 0.25] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Limited Time Offers -> CLICK\n[button] Show filter modal Category -> CLICK\n[button] Furniture 356 -> CLICK\n[button] + 11 more -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.671, 0.142, 0.925, 0.157] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all the artists with smith in their name\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: smith\n[button] SEARCH -> CLICK\n[button] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.107, 0.897, 0.134] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play the top track for the top indie artist in the last 30 days\nPrevious actions:\n[link] Music -> CLICK\n[link] indie -> CLICK\n[link] The Smiths -> CLICK\n[button] Sorted by: Last 7 days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.568, 0.713, 0.656, 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: Check the lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[textbox] Zip -> TYPE: 90012\n[button] Search -> CLICK\n[combobox] Select Minimum Year -> SELECT: 2017\n[combobox] Select Maximum Year -> SELECT: 2017\n[div] White -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.226, 0.429, 0.247] in the image\nAnd my action is Action: SELECT\nValue: Lowest price 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: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: stewart hotel\n[option] STEWART HOTEL  148 W 31st Street, New York Parking... -> CLICK\n[link] BOOK MONTHLY PARKING -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.43, 0.24, 0.457] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[span] Paris -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: MILAN\n[span] Milano (Milan) -> CLICK\n[textbox] Date use format: 01-Apr-23 -> CLICK\n[rect] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.226, 0.282, 0.24] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[button] Continue to flight results -> CLICK\n[link] Sort & Filter -> CLICK\n[svg] -> CLICK\n[label] Points -> CLICK\n[link] Sort & Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.183, 0.111, 0.439, 0.132] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for places to stay in Santa Fe, New Mexico for a weekend starting on Jun 16th for 3 guests and 2 rooms.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Santa Fe\n[span] Santa Fe, New Mexico, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.258, 0.396, 0.282] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[textbox] From -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.281, 0.434, 0.303] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.451, 0.044, 0.551, 0.072] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] 1 NIGHT Sun, Apr 09 - Mon, Apr 10 -> CLICK\n[span] 17 -> CLICK\n[span] 20 -> CLICK\n[button] Done -> CLICK\n[button] 1 Room, 1 Guest -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.151, 0.341, 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 used Xbox series X available.\nPrevious actions:\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox Series X|S -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK\n[button] Condition -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.288, 0.101, 0.3] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular tours and attractions in Kyoto, Japan from May 25 with free cancellation option, check availability for 2 adults and 1 infant, and book.\nPrevious actions:\n[div] Select your dates -> CLICK\n[svg] -> CLICK\n[checkbox] 25 May 2023 -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.269, 0.164, 0.28] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get email alerts for a flight from BHZ to EWN leaving on april 30 on the email [email protected]\nPrevious actions:\n[textbox] To , required. -> TYPE: ewn\n[a] EWN - Coastal Carolina Regional, NC -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 30 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.776, 0.244, 0.885, 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: Search for a flight on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[textbox] From -> TYPE: TEL AVIV\n[span] Tel Aviv -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.406, 0.117, 0.713, 0.129] in the image\nAnd my action is Action: TYPE\nValue: VENICE" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coupons and deals in New York.\nPrevious actions:\n[link] Coupons -> CLICK\n[input] -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.066, 0.788, 0.092] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[button] DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.103, 0.735, 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: Find the lowest-priced single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[link]  Computer Peripherals  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.344, 0.192, 0.366] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the full menu for AMC dine-in locations.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.421, 0.027, 0.524, 0.064] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\n[tab] MY TRIPS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.159, 0.128, 0.169] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the reservation made by James Smith in the United States with Confirmation Number 123456\nPrevious actions:\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK\n[combobox] Select Residency -> SELECT: UNITED STATES" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.347, 0.557, 0.387] 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 the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: san diego\n[button] Submit -> CLICK\n[span] Select store -> CLICK\n[link] Flatware -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.545, 0.359, 0.648, 0.386] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK\n[span] -> CLICK\n[textbox] From , required. -> TYPE: bhz" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.201, 0.393, 0.226] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.668, 0.146, 0.699, 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: Renew a existing KOA rewards account with the rewards number 1000000001 e postal code 10023\nPrevious actions:\n[link] REWARDS PROGRAM -> CLICK\n[link] PURCHASE OR RENEW NOW  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.102, 0.455, 0.112, 0.467] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[combobox] Reservation type -> SELECT: Pickup\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: Boston\n[span] Boston -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.634, 0.254, 0.653, 0.264] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[combobox] Destination -> CLICK\n[combobox] Destination -> TYPE: Tokyo\n[span] (HND) -> CLICK\n[combobox] Nationality -> CLICK\n[option] United States of America (USA) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.737, 0.426, 0.876, 0.454] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[link] Group Travel -> CLICK\n[link] Group Travel for Students -> CLICK\n[textbox] Destination -> TYPE: washington\n[menuitem] Washington D.C., DC, USA -> CLICK\n[textbox] Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.61, 0.29, 0.648, 0.303] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 attorney for divorce in Union City, NJ.\nPrevious actions:\n[input] -> TYPE: Union City Nj\n[link] Union City, NJ -> CLICK\n[button] Find -> CLICK\n[link] All -> CLICK\n[label] Divorce -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.308, 0.559, 0.329] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[button] Continue -> CLICK\n[textbox] Passengers / Class -> CLICK\n[button] Increase number of infant passengers -> CLICK\n[button] Confirm -> CLICK\n[button] Show flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.215, 0.727, 0.29] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[link] Route map -> CLICK\n[textbox] Pick an origin Pick a destination -> TYPE: Abbotsford\n[span] Abbotsford, WI -> CLICK\n[textbox] Enter a town, city or zipcode -> TYPE: Sheboygan\n[span] Sheboygan, WI -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.332, 0.125, 0.356] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[label] Month -> CLICK\n[div] Add guests -> CLICK\n[path] -> CLICK\n[button] increase value -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.078, 0.819, 0.103] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of children's program events in Illinois.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Events -> CLICK\n[button] All -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.381, 0.665, 0.93, 0.694] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket listing on floor B row 17 seat listing to Beyoncé music concert on Mon Aug 14 at 7:00pm.\nPrevious actions:\n[link] Beyonce -> CLICK\n[button] Filter by Date -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.455, 0.275, 0.487, 0.294] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Create flight status notification -> CLICK\n[span] -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK\n[textbox] To , required. -> TYPE: ewn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.242, 0.595, 0.266] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Discover Katy Perry and add bookmark to it and view all tracks.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.006, 0.675, 0.028] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[heading] CAR -> CLICK\n[combobox] Enter pick up city, airport name, or airport code. -> TYPE: Brooklyn Central\n[div] Brooklyn - Central (New York), US -> CLICK\n[textbox] Pickup -> 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 [0.296, 0.288, 0.326, 0.306] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight schedule between London and New York for April 7 and check the upgrade details of the noon flight.\nPrevious actions:\n[span] New York -> CLICK\n[generic] Apr 6, 2023 -> CLICK\n[option] Apr 7, 2023 -> CLICK\n[button] Search -> CLICK\n[link] View details -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.644, 0.666, 0.931, 0.72] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[link] S -> CLICK\n[div] Filter -> CLICK\n[RootWebArea] Women's Sports Bras | Under Armour -> CLICK\n[button] Show more -> CLICK\n[div] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.155, 0.829, 0.178, 0.843] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the best rated ukulele tab to my favorites\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: ukulele\n[b] ukulele -> CLICK\n[link] Tab -> CLICK\n[link] High rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.404, 0.327, 0.523, 0.344] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[span] Bournemouth -> CLICK\n[generic] 30 -> CLICK\n[div] -> CLICK\n[button] Search -> CLICK\n[button] Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.87, 0.273, 0.918] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] 04/11/2023 -> CLICK\n[link] 12, Wednesday April 2023 -> CLICK\n[link] Find Schedules -> CLICK\n[div] Earlier -> CLICK\n[generic] Press enter key to get details about this schedule -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.576, 0.875, 0.604] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[label] Armenia -> CLICK\n[label] Austria -> CLICK\n[label] Belgium -> CLICK\n[label] Bulgaria -> CLICK\n[div] Popular -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.844, 0.095, 0.948, 0.11] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of most popular upcoming game releases.\nPrevious actions:\n[link] New & Noteworthy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.219, 0.303, 0.235] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] July -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.24, 0.318, 0.254] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 available wine at Kroger.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.039, 0.249, 0.059] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Greenport to Oyster Bay Branch, starting with train and ending via bus with less than 1/2 mile walk.\nPrevious actions:\n[listitem] Oyster Bay, NY, USA -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[combobox] Start Journey -> SELECT: Train\n[combobox] End Journey -> SELECT: Bus\n[button] Done button - Press enter key to submit travel pre... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.287, 0.359, 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 the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[button] Sort by:Our top picks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.295, 0.473, 0.316] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[link] FIND A CAMPGROUND  -> CLICK\n[link] TRIP PLANNER  -> CLICK\n[textbox] Enter your Origin -> TYPE: Cheyenne\n[textbox] Enter your Destination -> TYPE: Helena\n[button] Get Directions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.41, 0.08, 0.578, 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: Find the fastest single stop flight fron JFK airport in New York to Male in Maldives on March 13\nPrevious actions:\n[span] Round-trip -> CLICK\n[tab] One-way -> CLICK\n[textbox] Flight origin input -> TYPE: new york\n[div] John F Kennedy Intl -> CLICK\n[textbox] Flight destination input -> TYPE: male" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.49, 0.145, 0.84, 0.182] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pedicure salon in New York and add two to favorites.\nPrevious actions:\n[input] -> TYPE: pedicure salon" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.407, 0.137, 0.586, 0.165] 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 two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[link] Free breakfast (18) -> CLICK\n[link] Pool (18) -> CLICK\n[generic] Price -> CLICK\n[label] 100 - 200 USD (6) -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.195, 0.329, 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: Add a pack of toilet paper and a bottle of laundry detergent to your Amazon cart with the lowest total price.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: toilet paper\n[button] Go -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.832, 0.047, 0.866, 0.052] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details for a Times Square parking lot that is wheelchair accessible.\nPrevious actions:\n[textbox] Search for parking -> TYPE: Times Square\n[li] Times Square, New York, NY, USA -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.31, 0.339, 0.336] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.112, 0.562, 0.151] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse cafes that have outdoor seating and is dog friendly.\nPrevious actions:\n[textbox] Find -> TYPE: cafe\n[span] Cafe -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK\n[checkbox] Outdoor Seating -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.513, 0.203, 0.529, 0.212] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking near any NBA arena to enter today after 5 pm and exit after 8 pm\nPrevious actions:\n[link] View All Stadiums -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.694, 0.351, 0.758, 0.364] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find rental charges for bikes in 37863.\nPrevious actions:\n[link] Find a Store -> CLICK\n[textbox] Enter ZIP or City, State -> TYPE: 37863\n[path] -> CLICK\n[generic] Bike shop Pigeon Forge -> CLICK\n[link] See services menu for Rentals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.925, 0.646, 0.944, 0.659] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter car accident lawyers in Stanford, CA, sort them by distane and find the phone number of the nearest one.\nPrevious actions:\n[input] -> TYPE: Stanford, CA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.17, 0.406, 0.205] in the image\nAnd my action is Action: TYPE\nValue: car accident lawyers" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check refund status for John Davis for ticket no. 1234567890123\nPrevious actions:\n[link] Receipts and refunds -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.55, 0.251, 0.562] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] 1 Room, 1 Guest -> CLICK\n[button] Add Rooms -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Children -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.23, 0.341, 0.244] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the cruises that go from Miami Florida to The Bahamas\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.362, 0.285, 0.422] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[menuitem] Buy -> HOVER\n[menuitem] New Cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.528, 0.496, 0.606] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\n[combobox] Search for anything -> TYPE: laptop\n[button] Search -> CLICK\n[input] -> CLICK\n[textbox] Minimum Value in $ -> TYPE: 400\n[textbox] Maximum Value in $ -> TYPE: 500" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.336, 0.176, 0.355] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for developer jobs in Dallas, Texas, and review details of the latest job then create an 8-day alert after signing in.\nPrevious actions:\n[link] We're hiring! Join our team , Opens another site i... -> CLICK\n[button] Careers -> CLICK\n[link] View All Jobs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.069, 0.416, 0.081] in the image\nAnd my action is Action: TYPE\nValue: developer" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vehicle at New York JFK International Airport May 2-May 5 for an owner above 25 years.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: New York JFK\n[option] New York JFK International Airport JFK Jamaica, 11... -> 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 [0.769, 0.269, 0.808, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: [email protected]\nPrevious actions:\n[link] Sign up for job posting alerts -> CLICK\n[span] -> CLICK\n[button] Subscribe -> CLICK\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.711, 0.214, 0.977, 0.257] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[heading] Wireless Bra (Ultra Relax) -> CLICK\n[checkbox] BROWN -> CLICK\n[button] ADD TO CART -> CLICK\n[button] CONTINUE SHOPPING -> CLICK\n[checkbox] PURPLE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.581, 0.906, 0.625] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[span] Vacation packages -> CLICK\n[textbox] From -> TYPE: san francisco\n[a] SFO - San Francisco International, CA -> CLICK\n[textbox] To -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.348, 0.168, 0.641, 0.179] in the image\nAnd my action is Action: CLICK" } ]