Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 84

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the price of Boys' INFANT UA SURGE 3 RUNNING SHOES. black color and 9K size\nPrevious actions:\n[div] Product Category -> CLICK\n[link] Shoes -> CLICK\n[div] Color -> CLICK\n[link] Refine by color: Black -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.233, 0.122, 0.248] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 what payment methods are available for monthly parking.\nPrevious actions:\n[link] SUPPORT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.58, 0.331, 0.604] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out what payment methods are available for monthly parking.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.379, 0.008, 0.431, 0.025] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[div] Jakarta, Special Capital Region of Jakarta -> CLICK\n[div] Choose date -> CLICK\n[div] Jun -> CLICK\n[generic] 1 -> CLICK\n[generic] 4 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.101, 0.953, 0.127] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: mens black hoodie\n[span] mens black hoodie -> CLICK\n[div] Size Range -> CLICK\n[link] Big & Tall (5,552) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.303, 0.037, 0.314] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[link] 20 -> CLICK\n[select] Select Pick-up Time -> SELECT: 04:00 PM\n[input] -> CLICK\n[button] Find Your Truck -> CLICK\n[button] Select Truck -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.355, 0.441, 0.388] in the image\nAnd my action is Action: TYPE\nValue: 250" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the location of the Altavista bus stop.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Bus stops -> CLICK\n[button] Altavista, VA  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.41, 0.269, 0.417] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two $50 playstation store gift cards to cart\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Gift Cards -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.172, 0.387, 0.266] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[button] Selected Pick-Up Date 03/21/2023 -> CLICK\n[button] Selected Return Date 03/22/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[span] 22 -> CLICK\n[button] 03/25/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.517, 0.364, 0.622, 0.392] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[link] Action Figures -> CLICK\n[img] Hasbro -> CLICK\n[button] All Filters -> CLICK\n[tab] Character -> CLICK\n[checkbox] Hulk -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.213, 0.393, 0.241] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find artist Mark Knight from London and follow him and add his most liked track to next up.\nPrevious actions:\n[searchbox] Search -> TYPE: Mark Knight\n[button] Search -> CLICK\n[link] Mark Knight -> CLICK\n[button] Follow -> CLICK\n[link] Popular tracks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.408, 0.222, 0.457, 0.232] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out if Coldplay is playing any events in Columbus, OH on May 17.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.124, 0.719, 0.149] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Premium Cars available to rent at LondonHeathrow Airport.\nPrevious actions:\n[label] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: London\n[div] London Heathrow Airport (LHR) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.156, 0.923, 0.206] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.038, 0.366, 0.061] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[span] Add to list -> CLICK\n[checkbox] Walgreens New -> CLICK\n[button] Done -> CLICK\n[button] Back -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.518, 0.193, 0.541] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[link] MEN -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.519, 0.137, 0.727, 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 the new arrivals on Easter home decor\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: easter home decor" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.081, 0.342, 0.103] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two $50 playstation store gift cards to cart\nPrevious actions:\n[button] Gift Cards -> CLICK\n[img] -> CLICK\n[img] -> CLICK\n[button] Add to Cart -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.283, 0.975, 0.306] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[use] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.765, 0.716, 0.789] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a list of Administrative and Clerical jobs MTA is currently recruiting for in Brooklyn\nPrevious actions:\n[link] Careers -> CLICK\n[link] See all open MTA positions. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.579, 0.663, 0.629] in the image\nAnd my action is Action: TYPE\nValue: brooklyn" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for Pizza making class in New York next month.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[combobox] Reservation type -> SELECT: Events\n[combobox] Event date -> SELECT: Next month" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.872, 0.312, 0.894, 0.326] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of flight #039028\nPrevious actions:\n[input] -> TYPE: 039028" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.59, 0.027, 0.603, 0.034] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the closest parking spot to the Orlando Magic at Brooklyn Nets event, happening in Barclays Center, to enter after 3 pm and exit after 5 pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: barclays center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK\n[p] Orlando Magic at Brooklyn Nets -> CLICK\n[select] Sort by Distance -> SELECT: Sort by Distance" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.27, 0.191, 0.307] in the image\nAnd my action is Action: SELECT\nValue: 3 00 PM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check all available tickets within $100 to $200 for the New York Knicks first game on April2 nd.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.269, 0.072, 0.311, 0.084] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.087, 0.129, 0.108] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 deals in California\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.26, 0.039, 0.309, 0.081] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[button] Search -> CLICK\n[button] 2 adults · 0 children · 1 room -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.108, 0.335, 0.331, 0.352] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[option] Finance -> CLICK\n[button] Time Type -> CLICK\n[searchbox] Search -> CLICK\n[option] Full time -> CLICK\n[button] SEARCH BY JOB TITLE OR KEYWORD -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.232, 0.571, 0.249] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for all Alternative Concerts taking place in New York City.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.67, 0.161, 0.683] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Railcard options for a 20 year old couple traveling within London and the South East\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK\n[menuitem] Railcards -> CLICK\n[combobox] How old are you? -> SELECT: 18-25" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.374, 0.349, 0.626, 0.377] in the image\nAnd my action is Action: SELECT\nValue: Couple" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for Pizza making class in New York next month.\nPrevious actions:\n[combobox] Event date -> SELECT: Next month\n[path] -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Pizza -> CLICK\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.328, 0.462, 0.358] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check bookstores available in Chelsea area\nPrevious actions:\n[link] shopping. -> CLICK\n[li] Neighborhood -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.437, 0.171, 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: 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[textbox] Enter your pick-up location or zip code -> TYPE: AUCKLAND\n[span] Auckland Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 7 -> CLICK\n[combobox] Pick Up Time -> SELECT: 10:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.27, 0.691, 0.304] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find wall mirrors for under $20.\nPrevious actions:\n[link] Mirrors -> CLICK\n[link] Wall mirrors -> CLICK\n[button] Show more filters modal -> CLICK\n[span] Price -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.644, 0.776, 0.806, 0.819] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 barbershops that have private lot parking.\nPrevious actions:\n[span] Barbershop -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK\n[span] -> CLICK\n[checkbox] Private Lot -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.427, 0.688, 0.448] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Increment -> CLICK\n[button] Increment -> CLICK\n[span] 0 -> TYPE: 7\n[tab] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.948, 0.124, 0.964, 0.138] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to cart 2 bottles of vitamin D that are buy 1 get 1 free and new arrival.\nPrevious actions:\n[button] Shop -> CLICK\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.174, 0.574, 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: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.436, 0.699, 0.458] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my favorites a cruise for 4 people going to Caribbean.\nPrevious actions:\n[button] SAIL TO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.72, 0.374, 0.863, 0.393] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[h1] My New Playlist -> CLICK\n[h1] My New Playlist -> TYPE: Dirty\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.662, 0.142, 0.688, 0.156] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[textbox] Enter ZIP or State -> TYPE: 07055\n[button] Set My Store -> CLICK\n[button] set store -> CLICK\n[button] Make -> CLICK\n[span] (954) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.147, 0.249, 0.167] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Save -> CLICK\n[button] Close -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[button] Add to playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.233, 0.712, 0.243] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 musical instruments and filter the results to show only those that are available for free local pickup.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: musical instruments\n[option] musical instruments -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.61, 0.08, 0.662, 0.096] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: book a reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[textbox] Search -> TYPE: Alinea\n[span] Chicago, IL - Lincoln Park -> CLICK\n[i] -> CLICK\n[i] -> CLICK\n[button] Go to next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.791, 0.352, 0.821, 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: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[menuitem] Free to home or store -> CLICK\n[button] Back to all categories -> CLICK\n[switch] COMPARE -> CLICK\n[path] -> CLICK\n[button] Add to Compare -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.816, 0.108, 0.899, 0.134] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.473, 0.125, 0.515, 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 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[checkbox] Free internet -> CLICK\n[button] Style -> CLICK\n[checkbox] Family -> CLICK\n[button] Amenities -> CLICK\n[checkbox] Air-conditioned -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.654, 0.136, 0.754, 0.151] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest return tickets from Leeds to Sheffield leaving at 8:30 am on Mar 25, 2023 and returning at 23:00 pm on same day for 1 adult and 2 child.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: Leeds\n[span] Leeds -> CLICK\n[span] Sheffield -> CLICK\n[textbox] Date use format: 24-Mar-23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.199, 0.252, 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: Add 10 of the cheapest green shirt to my cart\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: shirt\n[textbox] Search by keyword or web id -> ENTER\n[link] Sort by: Featured -> CLICK\n[link] Price Low-High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.268, 0.385, 0.424] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 press releases for the year 2020\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.468, 0.884, 0.536, 0.893] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add cheapest vitamin C and D to cart.\nPrevious actions:\n[button] Add CVS Health Vitamin C Tablets 250mg, 100CT to B... -> CLICK\n[img] -> CLICK\n[link] Vitamins A-Z -> CLICK\n[img] Vitamin D -> CLICK\n[div] Relevance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.823, 0.221, 0.98, 0.241] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[input] -> CLICK\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK\n[button] Listing options selector. List View selected. -> CLICK\n[link] Gallery View -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.686, 0.145, 0.775, 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: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[path] -> CLICK\n[checkbox] 10 May 2023 -> CLICK\n[checkbox] 12 May 2023 -> CLICK\n[button] Search -> CLICK\n[button] Choose your room -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.398, 0.324, 0.549, 0.347] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the planned service alerts for the subway red line\nPrevious actions:\n[link] subway Subway Lines -> CLICK\n[span] Red Line -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.204, 0.45, 0.249] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check Real Madrid player Vinicius Junior bio\nPrevious actions:\n[button] MORE -> CLICK\n[div] Soccer -> CLICK\n[link] La Liga La Liga -> CLICK\n[div] Real Madrid -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.049, 0.79, 0.073] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add cheapest vitamin C and D to cart.\nPrevious actions:\n[button] Shop -> CLICK\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.317, 0.574, 0.365] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\n[generic] Controller -> CLICK\n[span] Sony -> CLICK\n[button] APPLY -> CLICK\n[span] Free Shipping -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.135, 0.4, 0.149] in the image\nAnd my action is Action: SELECT\nValue: Highest Price" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 music party in Ohio and follow its organizer\nPrevious actions:\n[div] Search for events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.054, 0.326, 0.087] in the image\nAnd my action is Action: TYPE\nValue: music" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the budget price for the vehicle with most seats availible at Roanoke Regional Airport from April 5-6.\nPrevious actions:\n[button] Select My Car -> CLICK\n[link] Price (Low to High) -> CLICK\n[div] Sort by: -> CLICK\n[link] Number of Seats (High to Low) -> CLICK\n[link] Pay Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.812, 0.119, 0.93, 0.141] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[link] WOMEN -> CLICK\n[RootWebArea] Women's, Men's & Kids' Clothing & Accessories | UN... -> CLICK\n[searchbox] Search by keyword -> TYPE: women t-shirts" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.225, 0.637, 0.253] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 artist Mark Knight from London and follow him and add his most liked track to next up.\nPrevious actions:\n[button] Search -> CLICK\n[link] Mark Knight -> CLICK\n[button] Follow -> CLICK\n[link] Popular tracks -> CLICK\n[button] More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.327, 0.513, 0.346] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Change the language to UK English and the currency to Euros\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.565, 0.015, 0.579, 0.026] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[div] GBP -> CLICK\n[button] -> CLICK\n[div] £ -> CLICK\n[div] -> CLICK\n[textarea] -> TYPE: Happy Birthday Love" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.345, 0.916, 0.37] in the image\nAnd my action is Action: TYPE\nValue: Stuart Bloom" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.204, 0.26, 0.505, 0.296] in the image\nAnd my action is Action: TYPE\nValue: New Orleans" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[button] Shopping -> CLICK\n[link] GeekMarket -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.005, 0.51, 0.024] in the image\nAnd my action is Action: TYPE\nValue: king of tokyo" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all time popular drop c rock tab of beginner difficulty\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Beginner 554,088 -> CLICK\n[link] Drop C 3,930 -> CLICK\n[link] Rock 2,420 -> CLICK\n[link] Tab -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.824, 0.396, 0.97, 0.418] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Departure station, London selected. -> TYPE: edinburg\n[span] Edinburgh (Waverley) -> CLICK\n[combobox] Arrival station, Sheffield selected. -> TYPE: manchester" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.106, 0.326, 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: Search for a flight on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.104, 0.374, 0.115] in the image\nAnd my action is Action: TYPE\nValue: TEL AVIV" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[button] 19 -> CLICK\n[button] 23 -> CLICK\n[img] Add -> CLICK\n[img] Add -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.162, 0.686, 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: Browse hip hop concerts that are happening this weekend.\nPrevious actions:\n[button] CONCERTS -> CLICK\n[link] Rap / Hip Hop -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.382, 0.881, 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: Go to the list of ballet event for the next 30 days.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.256, 0.782, 0.304] in the image\nAnd my action is Action: TYPE\nValue: Ballet" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Pick Up Time -> SELECT: 10:00 AM\n[textbox] mm/dd/yyyy -> CLICK\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 5:00 PM\n[generic] Vehicle Type * -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.376, 0.782, 0.392] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate monthly payment for car value of $50,000 and downpayment of $10,000 with interest rate of 4% for 60 months.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.0, 0.279, 0.034] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[listitem] Honda (116) Honda (116) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Model -> CLICK\n[listitem] Civic (35) Civic (35) -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.539, 0.253, 0.583] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Charleston -> CLICK\n[textbox] zip or city, state -> TYPE: 25504\n[button] Look up -> CLICK\n[heading] Barboursville -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.238, 0.28, 0.248] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[strong] Doha -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 28 May 2023 -> CLICK\n[button] Continue -> CLICK\n[textbox] Passengers / Class -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.88, 0.412, 0.917, 0.429] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\n[div] hotels -> CLICK\n[textbox] Destination or property -> TYPE: Athens, Attica, Greeece" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.139, 0.128, 0.177, 0.137] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\n[menuitem] Women -> HOVER\n[menuitem] Golf -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.204, 0.233, 0.226] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK\n[textbox] To -> CLICK\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] Depart Date -> CLICK\n[gridcell] Tuesday, April 18, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.117, 0.156, 0.133] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Locations -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.84, 0.051, 1.051, 0.074] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search for restaurant that offers African Cuisine in east village under $30\nPrevious actions:\n[link] restaurants. -> CLICK\n[li] Cuisine -> CLICK\n[link] African -> CLICK\n[link] East Village (2) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.258, 0.207, 0.279] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking passes for New York Yankees game on April 14\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> CLICK\n[textbox] Search for artists, teams or venues... -> TYPE: New york yankees\n[option] New York Yankees -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.494, 0.941, 0.515] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[generic] next -> CLICK\n[generic] next -> CLICK\n[generic] next -> CLICK\n[generic] next -> CLICK\n[button] 10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.057, 0.373, 0.09, 0.392] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[button] 2010 -> CLICK\n[menuitem] 2018 -> CLICK\n[button] 2023 -> CLICK\n[menuitem] 2022 -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.338, 0.253, 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: I want to see mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[span] Mansions -> CLICK\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] Check in / Check out Any week -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.242, 0.613, 0.276] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a parking button code for my company Boston Legal located near Boston Navy Yard, and the button should be 160x400 pixels, and the parking spot should be within 15 miles of my address.\nPrevious actions:\n[textbox] STEP 1: Enter Your Company Name -> TYPE: BOSTON LEGAL\n[combobox] STEP 2:Enter an address to search and select a loc... -> TYPE: BOSTON NAVY YARD\n[em] Navy -> CLICK\n[span] 300 pixels x 150 pixels -> CLICK\n[span] 160 pixels x 400 pixels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.176, 0.73, 0.209, 0.744] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse xbox series x consoles that are used and between $200 and $400.\nPrevious actions:\n[combobox] Search for anything -> TYPE: xbox series x console\n[button] Search -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.356, 0.069, 0.372] in the image\nAnd my action is Action: TYPE\nValue: 200" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[combobox] Time -> SELECT: 10:00 AM\n[combobox] Party size -> SELECT: 4 guests\n[svg] -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Mediterranean -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.784, 0.506, 0.864, 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: Browse the list of action figure items available for pre order.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[link] Store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.031, 0.301, 0.054] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View details for a Times Square parking lot that is wheelchair accessible.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.138, 0.198, 0.73, 0.225] in the image\nAnd my action is Action: TYPE\nValue: Times Square" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Car rentals -> CLICK\n[searchbox] Please type your destination -> TYPE: mexico city\n[option] Mexico City - Benito Juarez Intl, MX (MEX) Mexico -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.827, 0.144, 0.927, 0.167] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the most popular documentary tv series sorted by IMDB rating, see the details of the top result.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Browse TV Shows by Genre -> CLICK\n[link] Documentary -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.326, 0.316, 0.339] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for places to stay in Santa Fe, New Mexico for a weekend starting on Jun 16th for 3 guests and 2 rooms.\nPrevious actions:\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Santa Fe\n[span] Santa Fe, New Mexico, United States -> CLICK\n[div] 16 -> CLICK\n[div] 18 -> CLICK\n[button] Increment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.904, 0.213, 0.92, 0.228] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate vehicle price with a challenge credit score, monthly payment of $250 with a $3000 down payment and 24% APR for 48 months in Tennessee.\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK\n[tab] Vehicle Price -> CLICK\n[textbox] Monthly Payment -> TYPE: 250\n[textbox] Down Payment -> TYPE: 3000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.308, 0.459, 0.337] in the image\nAnd my action is Action: SELECT\nValue: Tennessee" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 McDonalds located in Greenvill, SC.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.017, 0.564, 0.028] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get details of the fastest trip between 52nd Street,Brooklyn and 74th Street, Brooklyn, leaving now, that is accessible for a disabled person.\nPrevious actions:\n[searchbox] From -> TYPE: 52nd street, brooklyn\n[listitem] 52nd Street, Brooklyn, NY, USA -> CLICK\n[searchbox] To -> TYPE: 74th street, brooklyn\n[listitem] 74th Street, Brooklyn, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.244, 0.359, 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 Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[button] COLUMBUS, OH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.013, 0.284, 0.018] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK\n[div] -> CLICK\n[heading] to next step -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.384, 0.288, 0.63, 0.306] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 2 at a restaurant that was featured on the latest Hit List\nPrevious actions:\n[link] The Hit List -> CLICK\n[a] -> CLICK\n[link] Book Now -> CLICK\n[button] 12:30 PM Outdoor Counter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.418, 0.523, 0.459] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.163, 0.782, 0.21] in the image\nAnd my action is Action: TYPE\nValue: los angeles kings" } ]