Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show cheapest monthly price for parking near Shubert Theatre.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Shubert Theatre\n[option] Shubert Theatre  225 West 44th Street, New York De... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.09, 0.16, 0.123] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Watch the halftime show from the most recent Super Bowl\nPrevious actions:\n[use] -> CLICK\n[link] Super Bowl -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.439, 0.527, 0.561, 0.56] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[div] Columbus, OH -> CLICK\n[button] New York -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: indian\n[b] Indian -> CLICK\n[button] Today -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.257, 0.2, 0.285, 0.22] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[link] Title: IT Support Engineer -> CLICK\n[textbox] First Name (as per passport) (required) -> TYPE: James\n[textbox] Last Name (required) -> TYPE: Smith\n[textbox] Email (required) -> TYPE: [email protected]\n[checkbox] Career opportunity Career opportunity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.673, 0.71, 0.684, 0.721] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an LED TV below $1000.\nPrevious actions:\n[div] TV & Accessories -> CLICK\n[link] LED TV -> CLICK\n[dt] Price -> CLICK\n[textbox] price to -> TYPE: 1000\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.498, 0.18, 0.701, 0.26] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Children's Books -> CLICK\n[link] Non-Fiction -> CLICK\n[link] History -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.417, 0.196, 0.444] in the image\nAnd my action is Action: SELECT\nValue: Ages 9-11 (13,217)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[link] BABY -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.12, 0.257, 0.143] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 concerts taking place in Los Angeles, CA in the next month.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: Los Angeles\n[option] Los Angeles, CA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.174, 0.639, 0.268, 0.653] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 John Atas's trip with the confirmation number 1000001\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[li] My trips -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.721, 0.099, 0.731] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Pick-up date April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.185, 0.713, 0.211] in the image\nAnd my action is Action: SELECT\nValue: 9 00 am" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.086, 0.492, 0.123] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.115, 0.429, 0.459, 0.463] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the most recent NASCAR driver news.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.41, 0.179, 0.491, 0.217] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] Sort by -> CLICK\n[div] Top rated -> CLICK\n[link] Get tickets -> CLICK\n[p] Number of Travellers -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.669, 0.552, 0.825, 0.605] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 out about planned service changes on the 4 Subway on 5/3/2023.\nPrevious actions:\n[svg] -> CLICK\n[link] Planned Service Changes -> CLICK\n[searchbox] Search Routes -> TYPE: 4\n[listitem] 4 -> CLICK\n[button] 04/12/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.857, 0.199, 0.879, 0.212] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[link] FIND A CAMPGROUND  -> CLICK\n[link] TRIP PLANNER  -> CLICK\n[textbox] Enter your Origin -> TYPE: Cheyenne" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.231, 0.238, 0.265] in the image\nAnd my action is Action: TYPE\nValue: Helena" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List upcoming animation and anime movies in theaters\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK\n[link] COMING SOON -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.39, 0.415, 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: Show me all the events at any six flags park in Texas\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Fiesta Texas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.379, 0.844, 0.413] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel agents in Grand Junction, Colorado\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search the site -> TYPE: travel agent\n[button] Find -> CLICK\n[link] Find A Travel Agent | Carnival Cruise Line -> CLICK\n[textbox] City -> TYPE: Grand Junction" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.654, 0.334, 0.789, 0.354] in the image\nAnd my action is Action: SELECT\nValue: Colorado" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car options to pick up at any location near 10023 on april 12 at 3 am\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 12 -> CLICK\n[combobox] Pick Up Time -> SELECT: 3:00 AM\n[button] Select My Car -> CLICK\n[link] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.372, 0.567, 0.407] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.078, 0.273, 0.105] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the cruises that go from Miami Florida to The Bahamas\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] The Bahamas -> CLICK\n[button] SAIL FROM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.573, 0.28, 0.716, 0.313] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[svg] -> CLICK\n[span] Pickup -> CLICK\n[button] Change location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.133, 0.705, 0.148] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for los angeles kings this weekend\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: los angeles kings" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.162, 0.396, 0.179] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Austin -> CLICK\n[heading] New On Resy -> CLICK\n[button] Sat., Apr. 22 -> CLICK\n[button] April 21, 2023. -> CLICK\n[combobox] Party of 2 -> SELECT: 2 Guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.169, 0.144, 0.202, 0.155] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Activities  -> CLICK\n[textbox] Location-Search -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.332, 0.695, 0.372] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[button] Next -> CLICK\n[input] -> TYPE: Crew\n[input] -> TYPE: James\n[input] -> TYPE: Johnson" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.118, 0.777, 0.137] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[div] Vacations -> CLICK\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Europe\n[div] Europe -> CLICK\n[textbox] When? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.218, 0.106, 0.81, 0.135] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[textbox] ZIP Code -> TYPE: 70726\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 222900\n[button] Next -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.661, 0.166, 0.675] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[div] Texas City, TX -> CLICK\n[textbox] Select a date range. -> CLICK\n[img] Right -> CLICK\n[gridcell] Choose Saturday, April 22nd 2023. It's available. -> CLICK\n[gridcell] Choose Tuesday, April 25th 2023. It's available. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.619, 0.216, 0.774, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get email alerts for a flight from BHZ to EWN leaving on april 30 on the email [email protected]\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.211, 0.492, 0.241] in the image\nAnd my action is Action: TYPE\nValue: ewn" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movies for rent in the Redbox kiosk at any Winn Dixie in Daytona Beach.\nPrevious actions:\n[button] Navigate to Find a kiosk nearby -> CLICK\n[textbox] City or ZIP Code -> TYPE: Daytona\n[button] select to search for a kiosk using city or zipcode -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.124, 0.413, 0.15] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[div] Washington Dulles Intl Airport -> CLICK\n[generic] Vehicle Type * -> CLICK\n[p] SUVs & Wagons -> CLICK\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.172, 0.777, 0.19] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[label] Book with miles -> CLICK\n[LabelText] Enter pick up city, airport name, or airport code. -> TYPE: caldwell\n[div] Caldwell -> CLICK\n[textbox] Pickup -> CLICK\n[button] Saturday, April 8, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.436, 0.265, 0.457] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the ghost frame to your avatar using steam points.\nPrevious actions:\n[link] STORE -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.132, 0.388, 0.157] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pedicure salon in New York and add two to favorites.\nPrevious actions:\n[link] New York, NY -> CLICK\n[button] Find -> CLICK\n[link] Beauty & Youth Village Spa -> CLICK\n[use] -> CLICK\n[button] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.239, 0.323, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[combobox] Arrival station, none selected. Select a station. -> TYPE: LONDON\n[span] London Paddington -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 8 -> CLICK\n[listbox] hour -> SELECT: 14" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.227, 0.194, 0.247] in the image\nAnd my action is Action: SELECT\nValue: 00" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[button] Friday, April 14, 2023 -> CLICK\n[button] 1 Traveler -> CLICK\n[textbox] 1 Adults, 18 to 64 years old, 1 of 8 passengers se... -> TYPE: 1\n[combobox] undefined Selected 1 room -> CLICK\n[option] 1 room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.057, 0.518, 0.197, 0.543] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for all free virtual business start-up events happening tomorrow in Las Vegas and follow the organizer with most followers.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.283, 0.317, 0.495, 0.357] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 video highlights of the most recent Super Bowl.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.043, 0.787, 0.05] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car toll rate for bridges and tunnels\nPrevious actions:\n[span] Menu -> CLICK\n[span] Agencies -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.102, 0.234, 0.129] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[b] Indian -> CLICK\n[button] Today -> CLICK\n[button] April 12, 2023. -> CLICK\n[button] View more availability for BayLeaf Modern Indian C... -> CLICK\n[button] 8:15 PM Table -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.375, 0.523, 0.411] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[strong] New York -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 24 June 2023 -> CLICK\n[textbox] Passengers / Class -> CLICK\n[button] Decrease number of infant passengers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.889, 0.41, 0.927, 0.433] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[button] Search packages -> CLICK\n[button] Amenities -> CLICK\n[checkbox] Beachfront -> CLICK\n[checkbox] Hot tub -> CLICK\n[checkbox] Pool -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.8, 0.089, 0.812] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 me the cheapest red Model Y available to register in 94043\nPrevious actions:\n[link] Model Y -> CLICK\n[link] View Inventory -> CLICK\n[image] -> CLICK\n[combobox] Sort By -> SELECT: Price : low to high" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.048, 0.172, 0.273, 0.195] in the image\nAnd my action is Action: TYPE\nValue: 94043" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Need the cheapest small car on April 7, 10 am at Auckland airport for pick-up, return will be on April 10 at approx 5 pm.\nPrevious actions:\n[button] Reservations -> HOVER\n[link] Make a Reservation -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: AUCKLAND\n[span] Auckland Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.225, 0.691, 0.26] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[combobox] Sort by -> SELECT: Low to High\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.788, 0.338, 0.91, 0.366] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Buick for sale within 250 miles from 26807.\nPrevious actions:\n[link] Car Sales -> CLICK\n[combobox] All Makes -> CLICK\n[textbox] Zip Code: 43085 -> TYPE: 26807\n[combobox] 25 miles -> CLICK\n[generic] 250 miles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.441, 0.261, 0.47] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated mover in Honolulu to shift a vehicle and large appliances out of state and who has virtual discussion options available.\nPrevious actions:\n[link] Home Services -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.233, 0.115, 0.287, 0.143] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: COMFORTER\n[button] Go -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.436, 0.032, 0.446] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest cars available at San Francisco Airport for a day.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.63, 0.832, 0.642] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Discover Katy Perry and add bookmark to it and view all tracks.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: Katy Perry\n[button] Search -> CLICK\n[a] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.16, 0.133, 0.191, 0.157] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Girls -> CLICK\n[link] Jackets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.285, 0.233, 0.312] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\n[link] Route Map -> CLICK\n[textbox] From -> CLICK\n[textbox] From -> TYPE: Los Angeles\n[div] Los Angeles -> CLICK\n[textbox] To -> TYPE: Miami" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.007, 0.16, 0.293, 0.197] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 activities in Phuket, Thailand.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.148, 0.763, 0.158] in the image\nAnd my action is Action: TYPE\nValue: Phuket" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] 1 room, 2 travelers -> CLICK\n[img] Decrease adults in room 1 -> CLICK\n[button] Search -> CLICK\n[checkbox] Hotel -> CLICK\n[slider] price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.124, 0.825, 0.151] in the image\nAnd my action is Action: SELECT\nValue: Distance from landmark" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the list of movies \"at home\", sorted by most recent.\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK\n[link] AT HOME -> CLICK\n[span] Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.285, 0.43, 0.305] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Uncharted: Legacy of Thieves Collection to my guide and find the Queen's bracelet information.\nPrevious actions:\n[link] Guides -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.206, 0.148, 0.281, 0.188] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Thai restaurant and get notified when they have an open table between 5 to 7 PM\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: thai\n[heading] Senyai Thai Kitchen -> CLICK\n[button] Notify for Dinner -> CLICK\n[combobox] Preferred end time -> SELECT: 7:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.388, 0.75, 0.411] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the exotic vehicles they have available to rent?\nPrevious actions:\n[button] Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.272, 0.12, 0.289] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated dog collar under 10 dollar.\nPrevious actions:\n[link] Shop by Category -> CLICK\n[link] Pet -> CLICK\n[span] Pet Type -> CLICK\n[link] Dog (1,338) -> CLICK\n[span] Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.612, 0.146, 0.629] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[option] Las Vegas Nevada, United States -> CLICK\n[checkbox] 10 April 2023 -> CLICK\n[gridcell] 16 April 2023 -> CLICK\n[button] Search -> CLICK\n[button] Sort by:Our Top Picks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.274, 0.214, 0.448, 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: Purchase the classic bundle for the simulation game Cities Skylines.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Simulation -> CLICK\n[link] CITIES: SKYLINES -> CLICK\n[link] Bundle info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.368, 0.6, 0.389] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 luxury trip deal anywhere to go in spring\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Luxury Trips -> CLICK\n[div] Anywhere -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.586, 0.012, 0.781, 0.037] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 sleeping pad that is under $40.\nPrevious actions:\n[textbox] Search -> TYPE: black sleeping bag" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.269, 0.08, 0.3, 0.099] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with 4 star and above rating in Los Angeles for 3 days next week and save it.\nPrevious actions:\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Los Angeles\n[span] City -> CLICK\n[div] 21 -> CLICK\n[div] 23 -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.166, 0.194, 0.183] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[button] Water -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.156, 0.377, 0.17] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me routes from NYP to WAS on May 15th.\nPrevious actions:\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK\n[textbox] To -> TYPE: was\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] Depart Date -> CLICK\n[gridcell] Monday, May 15, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.824, 0.098, 0.957, 0.121] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[strong] Miami -> CLICK\n[span] 27 -> CLICK\n[textbox] Return Press DOWN ARROW key to select available da... -> CLICK\n[span] 31 -> CLICK\n[span] Search flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.17, 0.591, 0.217] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check all English Reading and Writing skills Educational Books for Ages 6-8 currently in stock that are available in hardback under 20$.\nPrevious actions:\n[link] Shop by category∨ -> CLICK\n[link] Ages 6-8 -> CLICK\n[link] Education -> CLICK\n[span] English Language -> CLICK\n[link] English Language: Reading & Writing Skills -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.291, 0.196, 0.305] in the image\nAnd my action is Action: SELECT\nValue: In Stock (41,088)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[link] SHOP ALL CARS -> CLICK\n[div] Best match -> CLICK\n[label] Lowest mileage -> CLICK\n[button] Back to all categories -> CLICK\n[heading] Distance & Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.292, 0.234, 0.313] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[textbox] First name -> TYPE: john\n[textbox] Last name -> TYPE: doew\n[textbox] Email address -> TYPE: [email protected]\n[textbox] Phone number -> TYPE: 4533234565\n[textbox] Social Security Number -> TYPE: 234567895" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.373, 0.698, 0.403] in the image\nAnd my action is Action: TYPE\nValue: 06/23/1992" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Make a Reservation -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[span] , United States -> CLICK\n[link] click here -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: Ohare, Chicago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.377, 0.352, 0.454, 0.37] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Los Angeles, California, and set Riverside as my store and add a card from that store to my favorites\nPrevious actions:\n[link] Find a store -> CLICK\n[p] 31 stores -> CLICK\n[span] see all stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.861, 0.465, 0.886] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the FareFinder to find flights for $150 or less from Dublin to anywhere.\nPrevious actions:\n[button] Plan -> CLICK\n[link] Fare Finder -> CLICK\n[textbox] From: -> CLICK\n[div] Dublin -> CLICK\n[textbox] To: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.369, 0.42, 0.432, 0.436] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[button] Increment -> CLICK\n[span] 0 -> TYPE: 7\n[tab] 7 -> CLICK\n[path] -> CLICK\n[div] 8+ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.163, 0.161, 0.177] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find JetBlue career openings in New York\nPrevious actions:\n[link] CareersExternal Link should open in a new window o... -> CLICK\n[textbox] Search by Location -> CLICK\n[textbox] Search by Location -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.455, 0.814, 0.474] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[polyline] -> CLICK\n[span] Youth -> CLICK\n[combobox] Select passenger age -> SELECT: 16\n[button] Done -> CLICK\n[listbox] hour -> SELECT: 12" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.318, 0.194, 0.346] in the image\nAnd my action is Action: SELECT\nValue: 00" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 skiing activity in August 10\nPrevious actions:\n[textbox] Where to? -> TYPE: skiing\n[button] When -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.227, 0.777, 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: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[tab] Flexible dates -> CLICK\n[label] Weekend -> CLICK\n[div] May -> CLICK\n[span] -> CLICK\n[span] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.156, 0.739, 0.165] in the image\nAnd my action is Action: TYPE\nValue: 100" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[link] Flatware & cutlery -> CLICK\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: san diego\n[button] Submit -> CLICK\n[span] Select store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.152, 0.186, 0.196] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 places that serve burgers in 44012 zip code and sort the results by highest rated\nPrevious actions:\n[span] Burgers -> CLICK\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: 44012\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 [0.518, 0.17, 0.612, 0.196] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find mens hiking shoes under $100 in size 10 that has biggest discount.\nPrevious actions:\n[div] Price -> CLICK\n[link] $10 to $25 (3) -> CLICK\n[link] $25 to $50 (18) -> CLICK\n[link] $50 to $100 (146) -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.515, 0.069, 0.525] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the current roster of the Miami Heat.\nPrevious actions:\n[link] NBA . -> HOVER\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.184, 0.197, 0.201] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Games & Puzzles in the Toys category that are suitable for ages 14+\nPrevious actions:\n[link] Categories -> CLICK\n[span] Toys -> CLICK\n[span] Games & Puzzles -> CLICK\n[button] Explore All -> CLICK\n[button] Age -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.421, 0.8, 0.432] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Open helpful links menu -> CLICK\n[link] Service & Repairs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.795, 0.822, 0.825] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Near -> TYPE: WESTMINSTER\n[span] Westminster -> CLICK\n[checkbox] Offers Takeout -> CLICK\n[button] Thai -> CLICK\n[button] See all -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.517, 0.247, 0.529, 0.257] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.057, 0.153, 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: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: changi\n[button] Singapore (SIN - Changi) Singapore -> CLICK\n[button] Departing April 5, 2023 -> CLICK\n[button] Apr 11, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.929, 0.359, 0.984, 0.377] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[span] Stony Brook -> CLICK\n[select] 1 -> SELECT: 10\n[select] 00 -> SELECT: 00\n[link] Find Schedules -> CLICK\n[link] Edit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.646, 0.427, 0.651, 0.446] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events at any six flags park in Texas\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Fiesta Texas -> CLICK\n[button] Go! -> CLICK\n[link] Events  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.622, 0.165, 0.735, 0.199] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check reservation availability for an Indian restaurant with price below $30 in East village\nPrevious actions:\n[link] restaurants. -> CLICK\n[li] Cuisine -> CLICK\n[link] Indian/Pakistani -> CLICK\n[link] East Village (9) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.534, 0.207, 0.55] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.047, 0.646, 0.063] in the image\nAnd my action is Action: TYPE\nValue: BATMAN" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 park in the state of California called Castle Mountains National Monument and find out it's Basic Information.\nPrevious actions:\n[button] Find a Park by State -> CLICK\n[link] California -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.571, 0.786, 0.672, 0.801] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fiction audio books sorted by lowest price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.068, 0.129, 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: book the cheapest hotel in Le maraise neighborhood in paris with 2 room for 3 adult on March 27th to April 2nd.\nPrevious actions:\n[button] Number of rooms and guests -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[div] Update -> CLICK\n[div] Distance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.552, 0.068, 0.765, 0.088] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.548, 0.01, 0.558] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look up information on the potential side effects of rogaine.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.014, 0.804, 0.035] in the image\nAnd my action is Action: TYPE\nValue: rogaine" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars with AWD with maximum budget of $50,000.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Cars for Sale -> CLICK\n[span] AWD/4WD -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.21, 0.284, 0.277, 0.3] in the image\nAnd my action is Action: TYPE\nValue: 50000" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 exercise events taking place in San Francisco between July 10-31.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.168, 0.939, 0.208] in the image\nAnd my action is Action: CLICK" } ]