Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[link] Fishing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.368, 0.206, 0.383] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order the cheapest climbing shoes in today's deals.\nPrevious actions:\n[link] Explore Deals -> CLICK\n[link] Climbing -> CLICK\n[combobox] Sort By -> SELECT: Price: Low - High\n[img] Black Diamond Zone Climbing Shoes 0 -> CLICK\n[button] Add to cart—$46.73 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.269, 0.202, 0.494, 0.22] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.32, 0.007, 0.393, 0.024] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[textbox] City Name -> TYPE: New York\n[select] Alabama -> SELECT: New York\n[textbox] Zip Code -> TYPE: 10001\n[textbox] (###) ###-#### -> TYPE: 888888888\n[textbox] Email Address -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.551, 0.463, 0.578] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[div] Vacations -> CLICK\n[textbox] Where? -> TYPE: mexico\n[div] Mexico -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.45, 0.135, 0.487, 0.171] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] ZIP Code -> TYPE: 49102\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 155000\n[button] Next -> CLICK\n[span] Black -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.448, 0.096, 0.467] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\n[span] Attractions -> CLICK\n[searchbox] Where are you going? -> TYPE: Aquarium of Paris\n[div] Aquarium of Paris -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.132, 0.732, 0.155] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the second most popular horror series to my watchlist.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.012, 0.1, 0.029] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the special timetable for Far Rockaway Branch of the Long Island Railroad.\nPrevious actions:\n[link] Schedules -> CLICK\n[heading] Long Island Rail Road & Metro-North Railroad -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.427, 0.5, 0.438] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Search -> CLICK\n[button] Recommended -> CLICK\n[div] Lowest Price -> CLICK\n[svg] -> CLICK\n[button] Choose your room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.233, 0.801, 0.308, 0.826] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 washable blue rug under 2'x3' size.\nPrevious actions:\n[link] Shop by Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.298, 0.159, 0.305] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a red used tesla Model S.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.054, 0.261, 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: Find a flight from Mumbai to New York City on 21st April, 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.053, 0.173, 0.088] in the image\nAnd my action is Action: TYPE\nValue: Mumbai" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[svg] -> CLICK\n[label] 9 -> CLICK\n[label] Available in Store -> CLICK\n[label] KEEN -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.499, 0.088, 0.513] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[span] 02199 -> CLICK\n[button] Continue -> CLICK\n[button] All Location Details -> CLICK\n[button] Selected Pick-Up Date 03/23/2023 -> CLICK\n[button] 03/27/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.31, 0.373, 0.336] in the image\nAnd my action is Action: SELECT\nValue: 11 00 AM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the BGG rules for Game Submissions?\nPrevious actions:\n[button] Help -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.486, 0.061, 0.571, 0.072] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Girls -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.163, 0.113, 0.172] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: O'hare Airport\n[heading] Chicago O'Hare International Airport -> CLICK\n[textbox] Drop-off location -> TYPE: 123 Main St, West Chicago, IL\n[heading] 123 Main St -> CLICK\n[button] pickup date input field -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.576, 0.315, 0.61, 0.331] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the cvs pharmacy nearest to zip code 45201 that provides hair loss evaluation and treatment.\nPrevious actions:\n[link] Explore all MinuteClinic health services -> CLICK\n[p] Skin, Hair & Nails -> CLICK\n[span] In-Person Care -> CLICK\n[button] Hair Loss Evaluation & Treatment -> CLICK\n[link] Hair Loss Evaluation & Treatment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.245, 0.34, 0.265] in the image\nAnd my action is Action: TYPE\nValue: 45201" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.528, 0.335, 0.539] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[span] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: SHANGHAI\n[div] Shanghai, China -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.297, 0.227, 0.471, 0.249] in the image\nAnd my action is Action: TYPE\nValue: SEOUL" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Price: low to high\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.336, 0.422, 0.348] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[textbox] From (type text or use the arrow keys) -> TYPE: Albany, NY\n[div] Albany, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Bloomington, NY\n[span] Bloomington, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.191, 0.721, 0.208] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the cheapest Women's Sweaters to my shopping cart.\nPrevious actions:\n[span] Shop by Category -> CLICK\n[link] Women -> HOVER\n[link] Sweaters & Cardigans -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.403, 0.974, 0.42] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse listings for a used 2006 Honda Civic.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.307, 0.211, 0.352] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: COMFORTER\n[button] Go -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.826, 0.032, 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: Show me the Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.211, 0.29, 0.241] in the image\nAnd my action is Action: TYPE\nValue: bhz" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wall mirrors for under $20.\nPrevious actions:\n[link] Products -> CLICK\n[button] Home décor -> CLICK\n[link] Mirrors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.166, 0.522, 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: Add games with the title Atlantis to my collection.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.76, 0.006, 0.995, 0.025] in the image\nAnd my action is Action: TYPE\nValue: Atlantis" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2022 highest goal scorer in the MLS league\nPrevious actions:\n[button] Soccer -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.215, 0.294, 0.371, 0.331] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play Trailer of \"The Flash\" 2023.\nPrevious actions:\n[textbox] Search IMDb -> CLICK\n[textbox] Search IMDb -> TYPE: The Flash" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.15, 0.193, 0.657, 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[button] Go! -> CLICK\n[div] Sort by -> CLICK\n[div] Lowest price -> CLICK\n[div] All dates -> CLICK\n[span] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.584, 0.128, 0.616, 0.136] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a gaming desktop with an rtx4000 GPU, available in stock.\nPrevious actions:\n[link]  Computer Systems  -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.239, 0.127, 0.434, 0.152] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[checkbox] 5 June 2023 -> CLICK\n[div] 1 days -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.214, 0.264, 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: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\n[link] Cancel my order -> CLICK\n[input] -> TYPE: James Smith\n[textbox] Email address used to place your order * -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.37, 0.759, 0.397] in the image\nAnd my action is Action: TYPE\nValue: X123456" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant with delivery service available 6pm on Mar 25th in Detroit, MI.\nPrevious actions:\n[combobox] Reservation type -> SELECT: Delivery\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: detroit" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.114, 0.734, 0.153] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check all available tickets within $100 to $200 for the New York Knicks first game on April2 nd.\nPrevious actions:\n[p] New York Knicks -> CLICK\n[link] View Tickets -> CLICK\n[span] (0) -> CLICK\n[textbox] Max Price -> TYPE: 200\n[textbox] Min Price -> TYPE: 100" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.571, 0.976, 0.628] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me routes from NYP to WAS on May 15th.\nPrevious actions:\n[textbox] From -> CLICK\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK\n[textbox] To -> TYPE: was" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.327, 0.147, 0.559, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.193, 0.312, 0.209] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Games & Puzzles in the Toys category that are suitable for ages 14+\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.046, 0.164, 0.076] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for restaurants near my location with pizza and for 6 customers.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: Pizza\n[b] Pizza -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.22, 0.562, 0.231] in the image\nAnd my action is Action: SELECT\nValue: 6 Guests" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[svg] -> CLICK\n[button] Choose your room -> CLICK\n[button] Book Business Double Room A -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.896, 0.302, 0.977, 0.331] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Find a receipt -> CLICK\n[radio] Confirmation or eTicket number -> CLICK\n[textbox] Confirmation or eTicket More information about con... -> TYPE: 12345678" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.295, 0.244, 0.499, 0.269] in the image\nAnd my action is Action: TYPE\nValue: Jason" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track my bus with service number SE4.\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK\n[tab] Service Number -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.212, 0.715, 0.255] in the image\nAnd my action is Action: TYPE\nValue: SE4" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[link] Proceed to checkout -> CLICK\n[button] Continue with this address -> CLICK\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.81, 0.492, 0.835] in the image\nAnd my action is Action: TYPE\nValue: 123456789" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a place with a good swimming pool that charges between $200 and $300 per night.\nPrevious actions:\n[img] -> CLICK\n[span] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.264, 0.202, 0.477, 0.213] in the image\nAnd my action is Action: TYPE\nValue: 200" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental cars in Seattle, WA and filter the results by the Best score.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Seattle\n[span] Seattle, Washington, United States -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.557, 0.14, 0.573, 0.149] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Done -> CLICK\n[button] 1 Room, 1 Guest -> CLICK\n[button] Add Rooms -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Adults -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.229, 0.341, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the budget price for the vehicle with most seats availible at Roanoke Regional Airport from April 5-6.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Roanoke" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.275, 0.279, 0.288] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.089, 0.293, 0.268, 0.322] in the image\nAnd my action is Action: TYPE\nValue: KATHMANDU" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 economy flight from Pune to New York in June and select the fully refundable.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: Pune\n[button] Pune, IN (PNQ) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: New York\n[button] New York, NY, US (NYC - All Airports) -> CLICK\n[button] Find flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.295, 0.646, 0.493] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[button] 15 -> CLICK\n[button] 16 -> CLICK\n[div] Petaluma Music Festival -> CLICK\n[button] Get tickets -> CLICK\n[listbox] Select quantity: General Admission price: $60.00 -> SELECT: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.471, 0.221, 0.573, 0.24] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[option] Top destination Tokyo, Japan (City) -> CLICK\n[div] 10 -> CLICK\n[span] 12 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.235, 0.393, 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.01, 0.323, 0.035] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Watch the halftime show from the most recent Super Bowl\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.013, 0.519, 0.021] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[link] Trip Ideas -> CLICK\n[div] Pacific Coast Highway Road Trip -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.046, 0.429, 0.069] in the image\nAnd my action is Action: TYPE\nValue: LOS ANGELES" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[img] Happy Birthday -> CLICK\n[button] EUR -> CLICK\n[div] GBP -> CLICK\n[button] -> CLICK\n[div] £ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.147, 0.167, 0.178, 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: Look up Popular Photos in the Community featuring Aegean Airlines\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.053, 0.742, 0.076] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse cough medicine that is rated 4 stars and above and is $15-$20.\nPrevious actions:\n[combobox] Search products and services -> TYPE: cough medicine" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.137, 1.0, 0.164] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find rental charges for bikes in 37863.\nPrevious actions:\n[link] Find a Store -> CLICK\n[textbox] Enter ZIP or City, State -> TYPE: 37863\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.232, 0.352, 0.281, 0.36] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.271, 0.459, 0.303] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] City -> TYPE: new york\n[textbox] Postcode/ZIP code -> TYPE: 10001\n[combobox] State -> TYPE: new york\n[textbox] Card number -> TYPE: 1234\n[combobox] Card type -> SELECT: MasterCard" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.381, 0.609, 0.416] in the image\nAnd my action is Action: SELECT\nValue: 01" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[button] 03/30/2023 -> CLICK\n[button] Browse Vehicles -> CLICK\n[checkbox] Trucks -> CLICK\n[combobox] SORT BY -> SELECT: Low to High\n[checkbox] 4+ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.19, 0.914, 0.209] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[input] -> TYPE: Stuart Bloom\n[input] -> TYPE: Denise\n[input] -> TYPE: Bloom\n[input] -> TYPE: [email protected]\n[input] -> TYPE: Debbi" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.373, 0.785, 0.627, 0.808] in the image\nAnd my action is Action: TYPE\nValue: Wolowitz" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Mens orange color Jacket and parkas with L Size and add to cart\nPrevious actions:\n[link] MEN -> HOVER\n[link] Jackets & Parkas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.353, 0.34, 0.647, 0.657] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate monthly payment for car value of $50,000 and downpayment of $10,000 with interest rate of 4% for 60 months.\nPrevious actions:\n[menuitem] Loan Calculator -> CLICK\n[input] -> TYPE: 50000\n[input] -> TYPE: 10000\n[input] -> CLICK\n[input] -> TYPE: 4" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.265, 0.34, 0.37, 0.373] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Panini Diamond Kings Baseball cards set below $25.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: Panini Diamonds Kings Baseball cards\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.26, 0.179, 0.385] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is [email protected], and phone number is 6157075521.\nPrevious actions:\n[combobox] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Corolla\n[combobox] Style -> SELECT: L Sedan 4D\n[button] Select Vehicle -> CLICK\n[button] No thanks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.035, 0.274, 0.371, 0.303] in the image\nAnd my action is Action: TYPE\nValue: ac recharge" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[button] Find Your Destination -> CLICK\n[link] Explore Destinations & Travel Requirements -> CLICK\n[combobox] Origin -> CLICK\n[combobox] Origin -> TYPE: New York\n[p] New York City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.216, 0.374, 0.242] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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[textbox] Event space -> TYPE: 7\n[button] Find -> CLICK\n[link]  All Filters -> CLICK\n[heading] Amenities  -> CLICK\n[label] Business center (11) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.538, 0.418, 0.556] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] Depart , required. -> TYPE: 04/21/2023\n[button] Add another flight -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: CDG" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.175, 0.393, 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: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[span] Jun 2023 -> CLICK\n[option] Oct 2023 -> CLICK\n[button] Search flights + cruise -> CLICK\n[label] October 08, 2023 -> CLICK\n[span] Nights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.727, 0.31, 0.744] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[textbox] Last name -> CLICK\n[textbox] Last name -> TYPE: COOPER\n[button] Search -> CLICK\n[button] Filter -> CLICK\n[combobox] Location -> SELECT: Arizona" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.383, 0.227, 0.512, 0.243] in the image\nAnd my action is Action: SELECT\nValue: Date - latest to soonest" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\n[span] San Francisco, CA -> CLICK\n[button] All -> CLICK\n[radio] Key extraction -> CLICK\n[radio] Vehicle -> CLICK\n[generic] 2 filters Key extraction • Vehicle Clear all Cance... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.563, 0.138, 0.66, 0.153] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 article about a new restaurant and share it on Twitter\nPrevious actions:\n[link] New Openings -> CLICK\n[a] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.472, 0.056, 0.483] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[tab] Select a Month -> CLICK\n[li] May -> CLICK\n[button] Filter -> CLICK\n[button] Adults-Only -> CLICK\n[button] Airfare Included -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.313, 0.772, 0.342] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[gridcell] 1 -> CLICK\n[span] -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.16, 0.342, 0.187, 0.368] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: new orleans\n[span] New Orleans, Louisiana, United States -> CLICK\n[textbox] Drop-off location -> TYPE: new york\n[span] New York, United States -> CLICK\n[generic] Saturday March 25th -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.539, 0.425, 0.572, 0.461] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\n[combobox] Search for anything -> TYPE: laptop" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.786, 0.027, 0.917, 0.052] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[i] -> CLICK\n[region] 4 Stars & Up -> CLICK\n[link] $50 to $100 -> CLICK\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.218, 0.458, 0.39, 0.536] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[div] Product Type -> CLICK\n[link] Jackets -> CLICK\n[div] Sports -> CLICK\n[link] Outdoor -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.294, 0.078, 0.324] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: london\n[span] London -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: sheffield\n[span] Sheffield -> CLICK\n[textbox] Date use format: 24-Mar-23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.294, 0.164, 0.311] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for used Jaguar XFs with no black exterior color and save the search as Jaguar to get a notification daily.\nPrevious actions:\n[button] Black (Exterior Color) -> CLICK\n[button] SAVE SEARCH -> CLICK\n[textbox] Custom name your search -> TYPE: Jaguar\n[button] CONTINUE -> CLICK\n[radio] Daily summary -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.418, 0.588, 0.449] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information regarding Fastbreak program.\nPrevious actions:\n[button] Fastbreak -> CLICK\n[link] Fastbreak Program -> CLICK\n[link] Join Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.689, 0.736, 0.783, 0.761] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[button] View Cart. Items in cart: 5 -> CLICK\n[div] Go to checkout -> CLICK\n[div] -> CLICK\n[button] Confirm address -> CLICK\n[p] Choose 3-hour window -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.433, 0.754, 0.483] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel deals in Las Vegas for four adults starting on May 17 and ending on May 20, and if deal is not available, set an alert for the same.\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.217, 0.152, 0.664, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[button] No -> CLICK\n[button] No -> 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 [0.165, 0.702, 0.284, 0.732] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Queen size memory foam mattress with lowest price.\nPrevious actions:\n[button] Products -> CLICK\n[button] Beds & mattresses -> CLICK\n[link] Mattresses -> CLICK\n[img] Foam and memory foam mattresses -> CLICK\n[button] Show sorting options modal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.311, 0.299, 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: Find a registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[link] Registry -> CLICK\n[button] Find a registry -> CLICK\n[textbox] First name -> CLICK\n[textbox] First name -> TYPE: SHELDON" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.389, 0.137, 0.588, 0.157] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\n[link] WOMEN -> HOVER\n[tab] Tops -> CLICK\n[link] T-Shirts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.256, 0.472, 0.264] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[combobox] Search by product -> TYPE: mirror\n[button] Search -> CLICK\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: atlanta georgia\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.863, 0.098, 0.981, 0.116] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the empire builder route in West US part of heartland and check the Minnesota stop.\nPrevious actions:\n[button] DESTINATIONS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.21, 0.303, 0.314] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[textbox] From -> CLICK\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK\n[textbox] To -> CLICK\n[option] Washington, DC - Union Station (WAS) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.604, 0.19, 0.712, 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: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[button] Saturday March 25, 2023 -> CLICK\n[generic] Saturday April 1st -> CLICK\n[button] Saturday April 1, 2023 -> CLICK\n[button] Noon -> CLICK\n[option] 2:00 pm -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.944, 0.088, 0.963, 0.098] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.203, 0.568, 0.22] in the image\nAnd my action is Action: TYPE\nValue: Alfred" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.466, 0.285, 0.484] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[button] Book -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.137, 0.109, 0.153] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[svg] -> CLICK\n[button] 04/08/2023 -> CLICK\n[combobox] Renter Age -> SELECT: 22\n[button] Vehicle Class -> CLICK\n[radio] Minivans -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.713, 0.357, 0.821, 0.379] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bananas at Kroger\nPrevious actions:\n[img] -> CLICK\n[textbox] Search Kroger... -> TYPE: bananas\n[span] bananas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.823, 0.18, 0.969, 0.212] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest likely to sell out activity in Los Angeles on April 2\nPrevious actions:\n[textbox] Where to? -> TYPE: Los Angeles\n[b] Los Angeles -> CLICK\n[button] Next -> CLICK\n[gridcell] Sun Apr 02 2023 -> CLICK\n[circle] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.233, 0.122, 0.243] in the image\nAnd my action is Action: CLICK" } ]