Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 87

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the balance for a gift card with the number 1000000000000000 and pin 1222\nPrevious actions:\n[link] Visit the Gift Cards page -> CLICK\n[link] Check Balance -> CLICK\n[spinbutton] Gift Card Number -> TYPE: 1000000000000000\n[spinbutton] Gift Card Pin -> TYPE: 1222" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.319, 0.5, 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 a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Kitchen -> CLICK\n[link] Kitchen Sinks -> CLICK\n[link] Drop In Two Bowl -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.313, 0.146, 0.327] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 kayaks and filter the results to show only those that are suitable for whitewater rapids.\nPrevious actions:\n[searchbox] Search -> CLICK\n[searchbox] Search -> TYPE: Kayaks\n[option] kayaks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.232, 0.164, 0.245] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[button] Plan -> CLICK\n[link] Try Somewhere New -> CLICK\n[link] Destinations -> CLICK\n[label] Armenia -> CLICK\n[label] Austria -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.202, 0.086, 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: 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[div] -> CLICK\n[textarea] -> TYPE: Happy Birthday Love\n[input] -> TYPE: Stuart Bloom\n[input] -> TYPE: Denise\n[input] -> TYPE: Bloom" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.797, 0.916, 0.832] 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: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NAPA VALLEY\n[span] Napa Valley -> CLICK\n[combobox] Reservation type -> SELECT: Wineries" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.568, 0.562, 0.586, 0.584] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[button] Leaving from -> CLICK\n[textbox] Leaving from -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: heathrow" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.147, 0.652, 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: Find tickets as gifts and book 2 tickets for stand-up comedian Dave Chappelle and the roots shows.\nPrevious actions:\n[link] Tickets as Gifts – Best Tickets to Buy Online -> CLICK\n[link] Dave Chapelle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.493, 0.941, 0.52] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[span] , Chicago -> CLICK\n[link] Make a Reservation -> CLICK\n[button] Select My Car -> CLICK\n[link] All Vehicles (13) -> CLICK\n[span] SUVs & Wagons (5) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.793, 0.474, 0.918, 0.509] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Renew a existing KOA rewards account with the rewards number 1000000001 e postal code 10023\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.68, 0.013, 0.799, 0.034] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[combobox] select-filter -> SELECT: 50 mi\n[span] Silver -> CLICK\n[p] Black -> CLICK\n[p] Lexus -> CLICK\n[p] Backup Camera -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.32, 0.429, 0.355] in the image\nAnd my action is Action: SELECT\nValue: Newest first (by car year)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[i] -> CLICK\n[span] SEARCH -> CLICK\n[tab] Lowest price first -> CLICK\n[checkbox] list-filter-item-label-0 -> CLICK\n[checkbox] list-filter-item-label-1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.509, 0.089, 0.517] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the photo gallery of Acadia National Park.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Photos & Multimedia -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.087, 0.641, 0.147, 0.652] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 CarMax in Michigan, 49107 and book an appointment for a car repair on April 7th..\nPrevious actions:\n[link] FIND A SHOP NEAR YOU -> CLICK\n[link] Find a Shop -> CLICK\n[li] 43065 -> TYPE: 49107\n[textbox] Zip Code -> TYPE: 49107\n[div] 49107 - Buchanan, MI -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.193, 0.45, 0.475, 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: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[div] -> CLICK\n[button] close -> CLICK\n[button] Flavor -> CLICK\n[div] -> CLICK\n[button] close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.349, 0.57, 0.39] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the artist profile of M S Subbulakshmi and play all from the top tracks.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: m s subbulakshmi\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.243, 0.146, 0.25] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[div] Make/Model -> CLICK\n[combobox] Year -> SELECT: 2016\n[combobox] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Camry\n[textbox] Mileage -> TYPE: 40000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.635, 0.206, 0.71, 0.226] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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: [email protected]\n[input] -> TYPE: Debbi\n[input] -> TYPE: Wolowitz\n[input] -> TYPE: [email protected]\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.823, 0.953, 0.853] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for 2 guests on april 21 at noon in a restaurant in Austin that is new on resy\nPrevious actions:\n[path] -> CLICK\n[button] Austin -> CLICK\n[heading] New On Resy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.206, 0.08, 0.215] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 career openings in the marketing department\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.217, 0.677, 0.255, 0.692] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[button] Thai -> CLICK\n[button] See all -> CLICK\n[checkbox] All staff fully vaccinated -> CLICK\n[checkbox] Accepts Apple Pay -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.077, 0.63, 0.085] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: trash can automatic lid\n[option] automatic trash can lid -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 60\n[button] Submit price range -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.75, 0.027, 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: check flight status for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Flight status -> CLICK\n[generic] Apr 7, 2023 -> CLICK\n[option] Apr 9, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.362, 0.161, 0.637, 0.189] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[span] Berlin -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: ZURICH\n[span] Zürich -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 31 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.268, 0.133, 0.291] in the image\nAnd my action is Action: SELECT\nValue: 08" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\n[tab] DEALS -> CLICK\n[link] Flights to popular destinations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.331, 0.263, 0.351] 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: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Jackets -> CLICK\n[div] Sports -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.325, 0.194, 0.333] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Manchester Piccadilly to any station in London on April 8, leaving nearest 10 AM for 1 adult\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> CLICK\n[combobox] Departure station, none selected. Select a station... -> TYPE: Manchester" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.128, 0.326, 0.159] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] -> CLICK\n[checkbox] Avis -> CLICK\n[button] More filters -> CLICK\n[checkbox] 4+ doors -> CLICK\n[spinbutton] Maximum price -> TYPE: 1000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.615, 0.563, 0.716, 0.582] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 alerts and conditions for the Alagnak Wild River.\nPrevious actions:\n[link] FIND A PARK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.108, 0.789, 0.128] in the image\nAnd my action is Action: TYPE\nValue: Alagnak" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Explore Destinations & Travel Requirements -> CLICK\n[combobox] Origin -> CLICK\n[combobox] Origin -> TYPE: New York\n[p] New York City -> CLICK\n[combobox] Destination -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.608, 0.374, 0.656] in the image\nAnd my action is Action: TYPE\nValue: Tokyo" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Sheffield -> CLICK\n[textbox] Date use format: 24-Mar-23 -> CLICK\n[link] 29 -> CLICK\n[listbox] Leaving at or Arrive by selector -> SELECT: Leaving at\n[listbox] hour -> SELECT: 10" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.21, 0.194, 0.228] in the image\nAnd my action is Action: SELECT\nValue: 45" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 hot seat VIP tickets through email id [email protected] for Adele's concert in Las Vegas on the last weekend of June.\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: adele\n[option] Adele -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.387, 0.941, 0.401] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[tab] Monthly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.106, 0.713, 0.132] in the image\nAnd my action is Action: TYPE\nValue: street taco" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest private sightseeing trip of India in the month of June\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.208, 0.463, 0.215] in the image\nAnd my action is Action: TYPE\nValue: India" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 black blazer for men with L size and add to wishlist.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: blazer\n[span] blazer -> CLICK\n[heading] Gender > Category -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.061, 0.274, 0.47, 0.292] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: SPRINGFIELD\n[button] Springfield, IL, US (SPI) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.194, 0.481, 0.221] in the image\nAnd my action is Action: TYPE\nValue: AUSTIN" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hair Loss Evaluation and Treatment in 10018 and show directions.\nPrevious actions:\n[button] load Health Services Menu -> CLICK\n[link] Skin, Hair & Nails -> CLICK\n[button] Hair Loss Evaluation & Treatment -> CLICK\n[link] Hair Loss Evaluation & Treatment -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> TYPE: 10018" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.421, 0.514, 0.454] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a tiny home anywhere for an adult and 2 pets to stay in from april 10 to april 12\nPrevious actions:\n[path] -> CLICK\n[span] Tiny homes -> CLICK\n[button] Check in / Check out Any week -> CLICK\n[button] 10, Monday, April 2023. Available. Select as check... -> CLICK\n[button] 12, Wednesday, April 2023. Available. Select as ch... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.621, 0.102, 0.737, 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: Check the availability of a Nintendo Switch gaming console at the nearest Target store.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: Nintendo Switch\n[link] nintendo switch -> CLICK\n[img] Nintendo Switch with Neon Blue and Neon Red Joy-Co... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.206, 0.769, 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: Search for Dining Room Sets under furniture and filter the results to show only items availble under the Buy It Now format.\nPrevious actions:\n[link] Home & Garden -> CLICK\n[button] Furniture -> CLICK\n[link] Dining Sets -> CLICK\n[button] Buying Format -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.83, 0.344, 0.971, 0.359] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a parking near any airport in california starting april 20 and ending april 23\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.323, 0.083, 0.333] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[link] Nearby Restaurants -> CLICK\n[div] Toronto -> CLICK\n[button] Chicago -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.232, 0.048, 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: Add a pack of toilet paper and a bottle of laundry detergent to your Amazon cart with the lowest total price.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: toilet paper\n[button] Go -> CLICK\n[span] Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.785, 0.065, 0.917, 0.077] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[searchbox] Search Site -> CLICK\n[searchbox] Search Site -> TYPE: Western Digital internal SSD 1 TB\n[button]  -> CLICK\n[link] Western Digital WD_BLACK SN770 M.2 2280 1TB PCIe G... -> CLICK\n[button] ADD TO CART  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.769, 0.254, 0.852, 0.268] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the best VIP seat to the Red Hot Chili Peppers 2023 Tour\nPrevious actions:\n[link] Music -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.401, 0.084, 0.41] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in New York City for 2 adults from Apr7 to Apr 8.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.228, 0.345, 0.234] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.393, 0.307, 0.406] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a virtual consultation for Solar Roof. The name is James Smith. The address is 123 st rd. The emial address is [email protected]\nPrevious actions:\n[link] Solar Roof -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.431, 0.418, 0.607, 0.43] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite the top rock track\nPrevious actions:\n[link] Music -> CLICK\n[link] rock -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.11, 0.176, 0.135, 0.193] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[link] Time: newly listed -> CLICK\n[button] Condition -> CLICK\n[link] Used -> CLICK\n[button] Style -> CLICK\n[link] French -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.53, 0.244, 0.603, 0.267] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[textbox] To -> TYPE: washington\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[div] Depart Date -> CLICK\n[button] Next month -> CLICK\n[gridcell] Thursday, June 1, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.307, 0.805, 0.325] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check flight status from London to New York City for next day.\nPrevious actions:\n[link] Flight status -> CLICK\n[textbox] From , required. -> TYPE: London\n[a] LON - London, United Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.381, 0.495, 0.62, 0.521] 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: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[link] click here -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: Ohare, Chicago\n[span] , United States -> CLICK\n[span] , Chicago -> CLICK\n[link] Make a Reservation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.337, 0.567, 0.384] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for an economy car in Houston from Mar 10 to Mar 13.\nPrevious actions:\n[button] Ellipsis Icon -> CLICK\n[link] Car rentals -> CLICK\n[textbox] Pick up -> TYPE: Houston" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.137, 0.255, 0.463, 0.274] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check flight status with flight number 2819 on 18th of March.\nPrevious actions:\n[tab] FLIGHT STATUS -> CLICK\n[button]  Search by date required selected as 15 March 202... -> CLICK\n[link] 18 March 2023, Saturday -> CLICK\n[button] done -> CLICK\n[spinbutton] Flight Number (Required) -> TYPE: 2819" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.894, 0.103, 0.934, 0.145] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[img] Madonna -> CLICK\n[link] Like A Virgin -> CLICK\n[button] Add to List -> CLICK\n[combobox] List -> SELECT: New\n[button] Save -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.46, 0.01, 0.469, 0.016] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.24, 0.0, 0.293, 0.038] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events happening at Madison Square Garden.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.219, 0.754, 0.235] in the image\nAnd my action is Action: TYPE\nValue: Madison Square Garden" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: download pdf for list of accessible station in NYC.\nPrevious actions:\n[span] Menu -> CLICK\n[link] Accessibility -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.521, 0.859, 0.542] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events in Lubbock, Texas during next 7 days\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.218, 0.782, 0.26] in the image\nAnd my action is Action: TYPE\nValue: Lubbock, Texas" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ed Sheeran Chords & Tabs\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.05, 0.838, 0.076] in the image\nAnd my action is Action: TYPE\nValue: Ed Sheeran" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[span] Youth -> CLICK\n[combobox] Select passenger age -> SELECT: 16\n[button] Done -> CLICK\n[listbox] hour -> SELECT: 12\n[listbox] minutes -> SELECT: 00" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.212, 0.327, 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: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.811, 0.035, 0.919, 0.061] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\n[link]  Gaming & VR  -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.434, 0.128, 0.63, 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 a veterinarian emergency service for dogs in Hawaii with a BBB rating of A+\nPrevious actions:\n[link] Hawaii, HI -> CLICK\n[button] Find -> CLICK\n[link] All -> CLICK\n[label] Veterinarians -> CLICK\n[label] Veterinarian Emergency Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.329, 0.204, 0.426, 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: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: berlin\n[button] Berlin Berlin Federal State, Germany (City) -> CLICK\n[div] -> CLICK\n[generic] 15 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.324, 0.236, 0.346, 0.251] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[radio] Price: low to high -> CLICK\n[path] -> CLICK\n[span] -> CLICK\n[path] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.95, 0.313, 0.969, 0.335] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search for Tree stands with at least 3 stars, and sort the results by price from low to high.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Climbing Stands -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.183, 0.222, 0.202] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the next available bus from Chicago to Ann Arbor.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Chicago\n[span] Chicago, IL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.172, 0.568, 0.194] in the image\nAnd my action is Action: TYPE\nValue: Ann Arbor" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: review the dinner menu of La Bergamote restaurant in Hell's Kitchen.\nPrevious actions:\n[link] restaurants. -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.261, 0.716, 0.286] in the image\nAnd my action is Action: TYPE\nValue: La Bergamote" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Sat 8 Apr - Sat 15 Apr -> CLICK\n[checkbox] 2 May 2023 -> CLICK\n[checkbox] 5 May 2023 -> CLICK\n[button] Search -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.186, 0.246, 0.203] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest vitamin C and D to cart.\nPrevious actions:\n[img] -> CLICK\n[link] Vitamins A-Z -> CLICK\n[img] Vitamin D -> CLICK\n[div] Relevance -> CLICK\n[div] Price Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.219, 0.263, 0.287, 0.284] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[button] Select My Car -> CLICK\n[link] Recommended -> CLICK\n[link] Price (Low to High) -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $16.99/Day$6.55/Day -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.654, 0.777, 0.677] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[button] enter zip or city, state -> CLICK\n[textbox] City -> CLICK\n[textbox] City -> TYPE: Cincinnati\n[combobox] State -> SELECT: OH\n[button] find store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.475, 0.208, 0.586, 0.231] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.007, 0.1, 0.018] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[tab] Travel Info -> CLICK\n[link] Shop Hotels -> CLICK\n[button] Going to -> TYPE: New Delhi\n[button] New Delhi Delhi, India -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.77, 0.204, 0.95, 0.235] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all Uniqlo's located in Chicago, IL.\nPrevious actions:\n[link] Store Locator -> CLICK\n[searchbox] SEARCH BY KEYWORD -> CLICK\n[searchbox] SEARCH BY KEYWORD -> TYPE: Chicago\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.821, 0.257, 0.977, 0.295] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wheelchair accessible parking for the Pittsburgh Pirates at St. Louis Cardinals event in Busch Stadium on Apr 13.\nPrevious actions:\n[textbox] Search for parking -> TYPE: busch stadium" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.109, 0.83, 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: book a tour to the statue of liberty for 3 adult on march 27th\nPrevious actions:\n[button] Check Availability -> CLICK\n[div] 27 -> CLICK\n[button] increase number -> CLICK\n[button] Apply -> CLICK\n[button] 10:30 AM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.761, 0.598, 0.962, 0.625] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest private sightseeing trip of India in the month of June\nPrevious actions:\n[button] India Asia -> CLICK\n[button] Next -> CLICK\n[path] -> CLICK\n[gridcell] Thu Jun 01 2023 -> CLICK\n[gridcell] Fri Jun 30 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.138, 0.78, 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: Follow Taylor Swift and add a playlist to next up.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.005, 0.561, 0.019] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ricky Kej track to listen and share which has been added in the last year and is between 2 to 10 minutes.\nPrevious actions:\n[link] Search for “Ricky Kej” -> CLICK\n[link] Tracks -> CLICK\n[link] Added any time -> CLICK\n[link] Past year -> CLICK\n[link] Any length -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.26, 0.212, 0.271] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: stewart hotel\n[option] STEWART HOTEL  148 W 31st Street, New York Parking... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.658, 0.286, 0.697] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[searchbox] Search Site -> CLICK\n[searchbox] Search Site -> TYPE: Western Digital internal SSD 1 TB\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.198, 0.451, 0.235] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[span] Vacation packages -> CLICK\n[textbox] From -> TYPE: san francisco" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.235, 0.385, 0.246] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: BWI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.203, 0.359, 0.223] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[generic] Tuesday April 4th -> CLICK\n[div] 7 -> CLICK\n[button] Tuesday April 11, 2023 -> CLICK\n[svg] -> CLICK\n[checkbox] Free internet -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.66, 0.249, 0.683] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 soonest upcoming event near zip code 90028.\nPrevious actions:\n[link] Events -> CLICK\n[button] Near you -> CLICK\n[textbox] Location search -> TYPE: 90028\n[span] 90028 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.396, 0.269, 0.459, 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: Show me current deals for California.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.26, 0.033, 0.309, 0.062] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the mystery vehicle to pick up at Bradenton in Mahattan, Florida on april 20 at 3 pm and return at 6pm\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Manhattan\n[div] Manhattan -> CLICK\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.211, 0.639, 0.237] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the list of injured NBA players.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.047, 0.335, 0.054] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dog collar under 10 dollar.\nPrevious actions:\n[link] Dog (1,338) -> CLICK\n[span] Category -> CLICK\n[link] Collars & Leashes (485) -> CLICK\n[link] Sort by: Featured -> CLICK\n[link] Highest Rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.565, 0.168, 0.582] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Toyota Corolla near 10019 and sort by cheapest.\nPrevious actions:\n[LabelText] Buy Used -> CLICK\n[combobox] Select Make -> SELECT: Toyota\n[combobox] Select Model -> SELECT: Corolla\n[textbox] Zip -> TYPE: 10019" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.601, 0.148, 0.748, 0.168] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Jerry Trainor's upcoming projects?\nPrevious actions:\n[textbox] Search IMDb -> TYPE: Jerry Trainor" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.009, 0.671, 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: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[polyline] -> CLICK\n[link] Cars for sale near Tampa, FL -> CLICK\n[checkbox] Third-Party Certified (343) -> CLICK\n[span] Drive Type -> CLICK\n[checkbox] Front Wheel Drive (147) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.342, 0.296, 0.384] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new books from Jk Rowling available for kids within the age from 3 to 5 that are below $20\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: Jk rowling\n[link] Jk rowling -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.684, 0.186, 0.834, 0.206] in the image\nAnd my action is Action: SELECT\nValue: Publication date, new to old" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most recently posted job opening in customer service in Ireland with a remote working option.\nPrevious actions:\n[link] Careers -> CLICK\n[div] Discover jobs around the world -> CLICK\n[ppc-content] Ireland -> CLICK\n[button] Flexible Workstyles -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.59, 0.329, 0.622] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wheelchair accessible parking for the Pittsburgh Pirates at St. Louis Cardinals event in Busch Stadium on Apr 13.\nPrevious actions:\n[textbox] Search for parking -> TYPE: busch stadium\n[li] Busch Stadium, Clark Avenue, St. Louis, MO, USA -> CLICK\n[p] Pittsburgh Pirates at St. Louis Cardinals -> CLICK\n[button] Filter -> CLICK\n[checkbox] Wheelchair Accessible (10) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.658, 0.458, 0.695] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hair Loss Evaluation and Treatment in 10018 and show directions.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.021, 0.265, 0.041] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[heading] CAR -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.237, 0.266, 0.273] in the image\nAnd my action is Action: TYPE\nValue: Brooklyn Central" } ]