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 a new address to the account. The address is 2983 Marietta Street, APT 2. Business name is Buck.\nPrevious actions:\n[span] 171 2nd street -> CLICK\n[textbox] Add a new address -> TYPE: 2983 Marietta Street\n[span] 2983 Marietta Street -> CLICK\n[textbox] Apt, floor, suite, etc (optional) -> TYPE: 2\n[textbox] Business name (optional) -> TYPE: Buck" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.65, 0.702, 0.702] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.058, 0.291, 0.078] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\n[combobox] Search for anything -> TYPE: iPhone 12 Pro" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.776, 0.031, 0.905, 0.048] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[button] Change Location -> CLICK\n[textbox] Enter ZIP or State -> CLICK\n[textbox] Enter ZIP or State -> TYPE: 07055\n[button] Set My Store -> CLICK\n[button] set store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.234, 0.249, 0.263] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: BERLIN\n[span] Berlin -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: ZURICH\n[span] Zürich -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.191, 0.194, 0.213] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get offer to sell car with AZ XA1234 number plate from Arizona state.\nPrevious actions:\n[LabelText] Sell My Car -> CLICK\n[textbox] Enter license plate -> TYPE: XA1234" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.513, 0.3, 0.583, 0.353] in the image\nAnd my action is Action: SELECT\nValue: AZ" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[input] -> TYPE: car accident lawyers\n[link] car accident lawyers -> CLICK\n[div] Sort: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.573, 0.203, 0.683, 0.238] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Metformin 1000mg tablet price and details.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] See All -> CLICK\n[link] Amazon Health -> CLICK\n[link] Amazon Pharmacy -> CLICK\n[span] Type your medication name -> TYPE: Metformin 1000mg" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.178, 0.55, 0.822, 0.587] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search for SkyMiles domestic Award Deals from Philadelphia to Atlanta.\nPrevious actions:\n[tab] SkyMiles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.064, 0.753, 0.071] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the list of movies \"at home\", sorted by most recent.\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK\n[link] AT HOME -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.413, 0.43, 0.43] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 terms and conditions of Amtrak RideReserve for Multi-Ride Passes\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.26, 0.026, 0.309, 0.053] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find rental charges for bikes in 37863.\nPrevious actions:\n[link] Find a Store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.157, 0.414, 0.175] in the image\nAnd my action is Action: TYPE\nValue: 37863" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[link] Careers -> CLICK\n[link] Open Jobs -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.494, 0.245, 0.54] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\n[textbox] Search -> TYPE: dog treats\n[span] dog treats -> CLICK\n[span] View all 20+ items -> CLICK\n[span] Best match -> CLICK\n[option] Price: lowest first -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.405, 0.19, 0.466, 0.21] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.35, 0.024, 0.391, 0.063] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated adventure game available for early access.\nPrevious actions:\n[link] Categories -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.116, 0.209, 0.127] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Check the status of a refund -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.255, 0.285, 0.301] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round trip flight with hotel on May 2 from Kathmandu, Nepal KTM to Shanghai, China PVG and return on May 5. Book a double room and check out with the default flights.\nPrevious actions:\n[link] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: KATHMANDU\n[div] Tribhuvan Intl Airport (KTM), Nepal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.155, 0.481, 0.179] in the image\nAnd my action is Action: TYPE\nValue: SHANGHAI" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 10 of the cheapest green shirt to my cart\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: shirt\n[textbox] Search by keyword or web id -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.273, 0.986, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.082, 0.041, 0.1] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[button] Locations -> CLICK\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: laguardia airport" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.34, 0.427, 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: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[link] Business Meetings  -> CLICK\n[textbox] Destination -> TYPE: new delhi\n[menuitem] New Delhi, Delhi, India -> CLICK\n[textbox] Start Date -> CLICK\n[gridcell] Sat, Apr 29, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.216, 0.394, 0.233] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights between SFO and EWR using the Boeing 787-9 aircraft\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.228, 0.469, 0.241] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest event to attend in Athens, Greece on April 2nd\nPrevious actions:\n[div] Events & Activities -> CLICK\n[input] -> CLICK\n[button] Greece -> CLICK\n[button] Athens -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.615, 0.209, 0.664, 0.225] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[tab] One-way -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.175, 0.432, 0.217] in the image\nAnd my action is Action: TYPE\nValue: New York City" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Xbox Wireless controller rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: xbox wireless controller\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.173, 0.192, 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: Browse climbing courses within 50 miles of 90028.\nPrevious actions:\n[link] Classes & Events -> CLICK\n[combobox] Activity -> SELECT: Climbing\n[textbox] Location -> TYPE: 90028" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.561, 0.218, 0.717, 0.241] in the image\nAnd my action is Action: SELECT\nValue: Within 50 miles" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse movies in theaters that are certified fresh and sorty by highest audience score.\nPrevious actions:\n[link] MOVIES -> CLICK\n[svg] -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.597, 0.802, 0.72, 0.84] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 current injuries of Phoenix Suns players.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.105, 0.335, 0.12] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[textbox] Zip Code -> TYPE: 60538\n[button] Search By Zip Code -> CLICK\n[button] MAKE MY STORE -> CLICK\n[textbox] Search by SKU, Model # or Keyword -> TYPE: Magtag electric dryer\n[button] Maytag in Electric Dryers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.183, 0.104, 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: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[tab] BOOK -> CLICK\n[link] Award travel -> CLICK\n[span] Flight + hotel -> CLICK\n[label] Basic Economy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.767, 0.326, 0.797] in the image\nAnd my action is Action: TYPE\nValue: las vegas" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[button] Done -> CLICK\n[path] -> CLICK\n[link] View More -> CLICK\n[img] -> CLICK\n[span] Add to list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.522, 0.309, 0.543] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights one way -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: JFK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.272, 0.393, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find 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[textbox] Enter VIN (17 digits) Where can I find the VIN -> TYPE: 1HGCM66543A064159\n[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 49102\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 155000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.189, 0.096, 0.219] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[button] Pick-up date April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[combobox] Pick-up time -> SELECT: 9:00 am" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.197, 0.931, 0.224] in the image\nAnd my action is Action: SELECT\nValue: 6 00 pm" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[label] 32\" -> CLICK\n[svg] -> CLICK\n[label] Less than $100 -> CLICK\n[span] Sort by: -> CLICK\n[div] Price (Low to High) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.476, 0.074, 0.488] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\n[searchbox] Search -> TYPE: SOUTH AFRICAN HISTORY PODCAST\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.089, 0.199, 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: Check the price of Tesla Model Y Performance for the 10001 zip code.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.39, 0.054, 0.454, 0.081] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\n[searchbox] Where are you going? -> TYPE: Aquarium of Paris\n[div] Aquarium of Paris -> CLICK\n[div] Select your dates -> CLICK\n[checkbox] 5 May 2023 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.137, 0.92, 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: I want to see mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[span] Mansions -> CLICK\n[button] Location Anywhere -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.441, 0.06, 0.518, 0.096] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[generic] Refine by Category: Consoles -> CLICK\n[checkbox] Microsoft Microsoft -> CLICK\n[button] Color -> CLICK\n[link] White -> CLICK\n[div] Condition -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.174, 0.107, 0.194] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Golden State Warriors Player List.\nPrevious actions:\n[button] Open Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.048, 0.931, 0.077] in the image\nAnd my action is Action: TYPE\nValue: Golden State Warriors" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking for 123456 last name Smith.\nPrevious actions:\n[tab] My Trips -> CLICK\n[textbox] booking reference -> TYPE: 123456" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.353, 0.323, 0.647, 0.359] 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 plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\n[span] Update ZIP code -> CLICK\n[span] See all bathroom boxes & baskets -> CLICK\n[button] Show filter modal Color -> CLICK\n[checkbox] Gray 12 products -> CLICK\n[button] Show filter modal Material -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.371, 0.308, 0.552, 0.334] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to favorites a cruise from San Francisco to the Panama Canal departing Oct 2024\nPrevious actions:\n[button] Panama Canal -> CLICK\n[span] Sail From -> CLICK\n[button] San Francisco, CA -> CLICK\n[span] Dates -> CLICK\n[button] October 2024 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.394, 0.871, 0.456] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the FareFinder to find flights for $150 or less from Dublin to anywhere.\nPrevious actions:\n[textbox] From: -> CLICK\n[div] Dublin -> CLICK\n[textbox] To: -> CLICK\n[div] Anywhere -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.71, 0.287, 0.824, 0.372] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 video game consoles and filter the results to show only those that have Wi-Fi Capability.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.196, 0.069, 0.246, 0.078] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way bus ticket between Albany, NY and Bloomington, NY April 10th and add the second one to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.197, 0.312, 0.226] in the image\nAnd my action is Action: TYPE\nValue: Albany, NY" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 red used tesla Model S.\nPrevious actions:\n[link] Model S -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.208, 0.491, 0.228] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find trip for 123456 last name Smith.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.892, 0.034, 0.963, 0.062] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find careers at the company on the Product Management team\nPrevious actions:\n[link] Company -> CLICK\n[link] Career Opportunities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.629, 0.46, 0.758, 0.488] in the image\nAnd my action is Action: SELECT\nValue: Product Management" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\n[span] Best match -> CLICK\n[option] Price: lowest first -> CLICK\n[span] Add -> CLICK\n[span] Add -> CLICK\n[button] Load more -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.608, 0.253, 0.715, 0.285] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.399, 0.34, 0.43] in the image\nAnd my action is Action: TYPE\nValue: 10003" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bookstores available in Chelsea area\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.064, 0.697, 0.074] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[gridcell] 20 -> CLICK\n[span] 01:30PM -> CLICK\n[link] 05:30PM -> CLICK\n[span] Apr 20 -> CLICK\n[gridcell] 21 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.835, 0.096, 0.896, 0.112] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[searchbox] From -> TYPE: Queensboro plaza\n[listitem] Queensboro Plaza Station, Long Island City, NY, US... -> CLICK\n[searchbox] To -> TYPE: Grand Central, NY\n[listitem] Grand Central Terminal, East 42nd Street, New York... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.475, 0.359, 0.514] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK\n[span] -> CLICK\n[textbox] Guest rooms -> TYPE: 1\n[textbox] Event space -> TYPE: 7" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.663, 0.605, 0.959, 0.635] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[span] Grand Central -> CLICK\n[searchbox] To -> CLICK\n[div] Recent Stations -> CLICK\n[searchbox] To -> TYPE: stoney brook\n[span] Stony Brook -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.67, 0.361, 0.727, 0.389] in the image\nAnd my action is Action: SELECT\nValue: 10" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show camping hammocks with lowest price first.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.048, 0.128, 0.067] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Washington airports to New York airports and only show those with scheduled status.\nPrevious actions:\n[link] Flight Finder -> CLICK\n[textbox] Origin -> TYPE: Washington\n[div] Washington -> CLICK\n[textbox] Destination -> TYPE: New York\n[div] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.924, 0.214, 0.936, 0.229] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car rentals in San Francisco for a weekend trip and filter the results by the rental company Avis and car type Economy.\nPrevious actions:\n[tab] Cars -> CLICK\n[textbox] Pick-up -> TYPE: San Francisco\n[button] San Francisco California, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.179, 0.277, 0.205] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 stats of the Athletic Club from spanish Laliga\nPrevious actions:\n[li] Soccer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.05, 0.36, 0.071] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\n[button] Xbox Series X|S -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK\n[button] Condition -> CLICK\n[checkbox] Pre-Owned Pre-Owned -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.046, 0.378, 0.079] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Limited Time Offers -> CLICK\n[button] Show filter modal Category -> CLICK\n[button] Furniture 356 -> CLICK\n[button] + 11 more -> CLICK\n[button] Furniture sets 138 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.671, 0.579, 0.835, 0.609] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a round trip from Phoenix to Miami with maximum budget of $2000.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.643, 0.263, 0.671] in the image\nAnd my action is Action: TYPE\nValue: Phoenix" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[link] Car Values -> HOVER\n[link] My Car's Value -> CLICK\n[div] Make/Model -> CLICK\n[combobox] Year -> SELECT: 2016" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.204, 0.187, 0.361, 0.208] in the image\nAnd my action is Action: SELECT\nValue: Toyota" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Confirm my vip tour at the six flags Discovery Kingdom\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Discovery Kingdom -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.062, 0.459, 0.07] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: indian\n[b] Indian -> CLICK\n[button] Today -> CLICK\n[button] April 12, 2023. -> CLICK\n[button] View more availability for BayLeaf Modern Indian C... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.193, 0.638, 0.354, 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: check the lowest price ticket for All star stand up comedy event happen 6pm on the 25th March 2023.\nPrevious actions:\n[link] concerts. -> CLICK\n[textbox] Search by Name -> TYPE: all star stand up comedy\n[p] All Star Stand Up Comedy -> CLICK\n[link] View Tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.909, 0.194, 0.991, 0.229] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[button] Selected Return Date 03/22/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[span] 22 -> CLICK\n[button] 03/25/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.263, 0.837, 0.289] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest private sightseeing trip of India in the month of June\nPrevious actions:\n[textbox] Where to? -> TYPE: India\n[button] India Asia -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.216, 0.777, 0.223] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\n[textbox] Flight origin input -> TYPE: madurai\n[div] Madurai, Tamil Nadu, India -> CLICK\n[path] -> CLICK\n[button] Search -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.564, 0.101, 0.579] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a woman t-shirt in xl size from merchandise section, add 2 pieces to the cart and check out.\nPrevious actions:\n[link] Merchandise -> CLICK\n[span] Women's Last.fm Spiral Hex Tee -> CLICK\n[select] S -> SELECT: XL\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.212, 0.757, 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: Show me the planned service alerts for the subway red line\nPrevious actions:\n[link] subway Subway Lines -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.218, 0.339, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] No -> CLICK\n[radio] Owned -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.695, 0.156, 0.719] in the image\nAnd my action is Action: CLICK" } ]

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

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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] Order Now -> CLICK\n[textbox] Shipping Address -> TYPE: 7528 East Mechanic Ave. Fargo, ND 58102\n[textbox] Shipping Address -> ENTER\n[spinbutton] Home Square Footage -> TYPE: 200\n[combobox] Number of Stories -> SELECT: Two-Story" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.713, 0.793, 0.963, 0.83] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Save two deals and offers for US.\nPrevious actions:\n[button] Deals -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.028, 0.598, 0.041] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[label] High-speed Internet (11) -> CLICK\n[button] APPLY -> CLICK\n[generic] Distance -> CLICK\n[label] 0 - 5 Miles (2) -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.467, 0.944, 0.503] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: HOLLYWOOD\n[span] Hollywood -> CLICK\n[button] 19 -> CLICK\n[button] 23 -> CLICK\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.437, 0.393, 0.45] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City from June 5th to 9th.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: New York City" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.196, 0.748, 0.218] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show computer game reviews sorted by score.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.129, 0.047, 0.145] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Begin booking a 14 day cruise from Los Angeles to Hawaii\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.448, 0.285, 0.504] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[tab] BOOK -> CLICK\n[link] Award travel -> CLICK\n[span] Flight + hotel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.283, 0.404, 0.414, 0.427] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gaming pc which can run Call of Duty Warzone at 4k.\nPrevious actions:\n[generic] Site Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.116, 0.196, 0.137] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the most recent NASCAR driver news.\nPrevious actions:\n[link] NASCAR Cup Series NASCAR -> CLICK\n[button] Open More Dropdown -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.766, 0.078, 0.978, 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: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[div] -> CLICK\n[link] 20 -> CLICK\n[select] Select Pick-up Time -> SELECT: 04:00 PM\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.546, 0.352, 0.587] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gaming desktop with an rtx4000 GPU, available in stock.\nPrevious actions:\n[link]  Computer Systems  -> HOVER\n[link] Gaming Desktops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.627, 0.158, 0.658] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harrt Reid Intl Airport, LAS\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[generic] Close -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 31 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.172, 0.858, 0.185] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 store in Los Angeles, California, and set Riverside as my store and add a card from that store to my favorites\nPrevious actions:\n[link] Find a store -> CLICK\n[p] 31 stores -> CLICK\n[span] see all stores -> CLICK\n[button] SET AS MY STORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.154, 0.291, 0.175] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Thai restaurant and get notified when they have an open table between 5 to 7 PM\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: thai\n[heading] Senyai Thai Kitchen -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.127, 0.205, 0.235, 0.232] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[gridcell] 21 -> CLICK\n[span] 07:30PM -> CLICK\n[link] 05:30AM -> CLICK\n[button] SEARCH -> CLICK\n[span] Distance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.005, 0.2, 0.128, 0.227] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse candle holder red decor products.\nPrevious actions:\n[link] Marketplace -> CLICK\n[link] Shop by Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.576, 0.139, 0.587] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a fully electric car pickup at Athens Airport (ATH) Sat, Apr 1, 2023 and return to the same palce at Mon, Apr 3, 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.154, 0.066, 0.263, 0.106] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check prices for luxury sedan car in Houston with insurance.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Houston" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.177, 0.446, 0.198] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] Events & Activities -> CLICK\n[input] -> CLICK\n[button] Spain -> CLICK\n[button] All cities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.599, 0.121, 0.652, 0.149] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK\n[checkbox] list-filter-item-label-4 -> CLICK\n[checkbox] list-filter-item-label-12 -> CLICK\n[checkbox] list-filter-item-label-3 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.729, 0.089, 0.737] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Thai restaurant and get notified when they have an open table between 5 to 7 PM\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: thai\n[heading] Senyai Thai Kitchen -> CLICK\n[button] Notify for Dinner -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.372, 0.607, 0.404] in the image\nAnd my action is Action: SELECT\nValue: 7 00 PM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[combobox] Return Time -> SELECT: 11:00 AM\n[textbox] Return to same location -> TYPE: washington\n[div] Washington Dulles Intl Airport -> CLICK\n[generic] Vehicle Type * -> CLICK\n[p] SUVs & Wagons -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.193, 0.567, 0.213] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[link] Rent a Moving Truck Budget Truck -> CLICK\n[textbox] US City,State or Zip Code -> TYPE: 07718\n[textbox] mm/dd/yyyy -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.372, 0.334, 0.403, 0.353] in the image\nAnd my action is Action: CLICK" } ]