Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Begin booking a 14 day cruise from Los Angeles to Hawaii\nPrevious actions:\n[span] Sail To -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.369, 0.568, 0.407] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find fitness events for this weekend.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.081, 0.939, 0.104] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Tokyo for two adults and one child, with a budget of $500 per night for 2 nights starting on May 5th.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[generic] Japan -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.277, 0.658, 0.285] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.282, 0.528, 0.327] in the image\nAnd my action is Action: TYPE\nValue: mexico city" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: LOS ANGELES\n[span] Los Angeles Intl Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[select] April 2023 -> SELECT: July 2023\n[link] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.345, 0.693, 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 a job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[link] Careers This link will take you away from the Qata... -> CLICK\n[span] 64 -> CLICK\n[textbox] Location -> TYPE: india\n[link] Mumbai - BOM, India - IN 2 jobs -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.609, 0.241, 0.633] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[link] Electronic -> CLICK\n[img] Madonna -> CLICK\n[link] Like A Virgin -> CLICK\n[button] Add to List -> CLICK\n[combobox] List -> SELECT: New" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.325, 0.417, 0.373, 0.441] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Gloomhaven's ratings?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.76, 0.005, 0.995, 0.023] in the image\nAnd my action is Action: TYPE\nValue: gloomhaven" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[heading] Supima® Cotton V-Neck Short-Sleeve T-Shirt (2022 E... -> CLICK\n[checkbox] L -> CLICK\n[button] ADD TO CART -> CLICK\n[button] VIEW CART -> CLICK\n[button] CHECKOUT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.344, 0.23, 0.628, 0.307] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[textbox] Zip Code -> TYPE: 60538\n[link] Store Locator   -> CLICK\n[textbox] Zip Code -> TYPE: 60538\n[button] Search By Zip Code -> CLICK\n[button] MAKE MY STORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.437, 0.042, 0.837, 0.058] in the image\nAnd my action is Action: TYPE\nValue: Magtag electric dryer" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gift registry of Carla Cahill, when asked for password use Michael Cahill as name and [email protected] as email.\nPrevious actions:\n[span] Find a Registry -> CLICK\n[textbox] First Name -> TYPE: Carla\n[textbox] Last Name -> TYPE: Cahill\n[link] SEARCH -> CLICK\n[span] View -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.442, 0.571, 0.46] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[textbox] Select date (format month/day/year) -> CLICK\n[button] 03/18/2023 -> CLICK\n[link] 25, Saturday March 2023 -> CLICK\n[radio] Arrive by -> CLICK\n[select] 1 -> SELECT: 9" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.319, 0.284, 0.34] in the image\nAnd my action is Action: SELECT\nValue: 45" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[checkbox] Tortillas (4) -> CLICK\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.812, 0.495, 0.99, 0.512] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the video highlights of the most recent Super Bowl.\nPrevious actions:\n[svg] -> CLICK\n[link] Super Bowl -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.438, 0.97, 0.567] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[button] Same as pick-up -> CLICK\n[textbox] Same as pick-up -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Pick-up date April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.236, 0.494, 0.278, 0.537] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] load Vitamins A-Z Menu -> CLICK\n[link] Vitamin C -> CLICK\n[div] Relevance -> CLICK\n[div] Price Low to High -> CLICK\n[img] CVS Health Vitamin C Tablets 250mg, 100CT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.672, 0.644, 0.812, 0.689] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find trip for 123456 last name Smith.\nPrevious actions:\n[button] MY TRIP -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.384, 0.112, 0.616, 0.123] in the image\nAnd my action is Action: TYPE\nValue: 123456" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Los Angeles, California, and set Riverside as my store and add a card from that store to my favorites\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.729, 0.107, 0.739] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[listitem] 52nd Street, Brooklyn, NY, USA -> CLICK\n[searchbox] To -> TYPE: 74th street, brooklyn\n[listitem] 74th Street, Brooklyn, NY, USA -> CLICK\n[label] Accessible Trip -> CLICK\n[link] Plan my Trip - Press enter key to submit the form ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.232, 0.324, 0.332, 0.359] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[link] 246,685 CD -> CLICK\n[link] 122,512 Album -> CLICK\n[link] Show more… -> CLICK\n[link] 1,342 2016 -> CLICK\n[link] 98 £15 - £20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.176, 0.331, 0.189] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.074, 0.036, 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: Find the highest-rated adults-only romantic beach vacation deals and book the cheapest one.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.781, 0.111, 0.902, 0.135] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[combobox] Minimum Year -> SELECT: 2018\n[combobox] Maximum Year -> SELECT: 2018\n[button] Make  -> CLICK\n[checkbox] Honda (549) -> CLICK\n[checkbox] Civic (122) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.775, 0.213, 0.888, 0.244] in the image\nAnd my action is Action: SELECT\nValue: Price - Lowest" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[button] April 20, 2023. -> CLICK\n[combobox] Party of 2 -> SELECT: 7 Guests\n[svg] -> CLICK\n[button] View more availability for Canal Street Eatery & M... -> CLICK\n[button] 2:00 PM Eatery -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.36, 0.523, 0.395] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Save two deals and offers for US.\nPrevious actions:\n[button] Deals -> HOVER\n[button] Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.04, 0.749, 0.059] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.033, 0.553, 0.059] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\n[link] Flights to popular destinations -> CLICK\n[textbox] Input departure airport -> TYPE: New York\n[textbox] Input arrival airport -> TYPE: Honolulu\n[option] Honolulu, HI, US (HNL) -> CLICK\n[textbox] Budget. Please enter a numerical value -> TYPE: 1300" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.738, 0.533, 0.793, 0.545] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 latest action tv shows which are rated fresh by both the audience and the rotten tomatoes\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[span] Sort: Most popular -> CLICK\n[span] Newest -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.354, 0.553, 0.477, 0.577] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a hybrid job at Resy in software development, if the job is open apply immediately.\nPrevious actions:\n[link] Careers -> CLICK\n[link] View All Open Positions -> CLICK\n[span] Filters -> CLICK\n[a] Software Development -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.328, 0.426, 0.345] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.022, 0.426, 0.043] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] All dates -> CLICK\n[span] -> CLICK\n[span] 1 -> CLICK\n[div] Sort by -> CLICK\n[div] Top rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.172, 0.892, 0.189] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop 2-5 day cruises to the Caribbean from Miami during August 2023.\nPrevious actions:\n[link] 2-5 DAY CRUISES Get big savings! Check out 2-5 day... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.044, 0.248, 0.075] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[img] -> CLICK\n[img] -> CLICK\n[button] Add to Cart -> CLICK\n[img] -> CLICK\n[button] Add to Cart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.625, 0.23, 0.984, 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: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[p] New York City -> CLICK\n[combobox] Destination -> CLICK\n[combobox] Destination -> TYPE: Tokyo\n[span] (HND) -> CLICK\n[combobox] Nationality -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.226, 0.562, 0.254] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 schedule of the East Boston ferry, check connections, and fares and download the pdf schedule.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.011, 0.369, 0.032] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurants, open 24 hours, and sorted by rating.\nPrevious actions:\n[link] Restaurants -> CLICK\n[link] OPEN 24 Hours -> CLICK\n[link] Default -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.573, 0.292, 0.683, 0.335] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.075, 0.355, 0.086] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: stewart hotel\n[option] STEWART HOTEL  148 W 31st Street, New York Parking... -> CLICK\n[link] BOOK MONTHLY PARKING -> CLICK\n[textbox] First Name -> CLICK\n[textbox] First Name -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.303, 0.463, 0.337] in the image\nAnd my action is Action: TYPE\nValue: SMith" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest news and rumors about the NBA team the Los Angeles Lakers.\nPrevious actions:\n[link] NBA . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.437, 0.126, 0.47, 0.139] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 kids 13Y size t shirts and add 3 to cart.\nPrevious actions:\n[link] T-Shirts -> CLICK\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK\n[svg] -> CLICK\n[img] AIRism Cotton Graphic Short-Sleeve Raglan T-Shirt -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.18, 0.803, 0.201] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car options to pick up at any location near 10023 on april 12 at 3 am\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: 10023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.272, 0.261, 0.312, 0.273] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: washington\n[span] Washington County Regional Apo -> CLICK\n[link] Make a Reservation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.116, 0.691, 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: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[link] Plan a trip to see fares. -> CLICK\n[searchbox] From -> TYPE: grand central\n[span] Grand Central -> CLICK\n[searchbox] To -> CLICK\n[div] Recent Stations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.361, 0.474, 0.391] in the image\nAnd my action is Action: TYPE\nValue: stoney brook" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of BGG shirts for sale\nPrevious actions:\n[button] Shopping -> CLICK\n[link] BGG Store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.369, 0.068, 0.376, 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: Find exercise events taking place in San Francisco between July 10-31.\nPrevious actions:\n[link] Sports & Fitness -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.014, 0.268, 0.245, 0.297] in the image\nAnd my action is Action: TYPE\nValue: San Francisco" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\n[div] -> CLICK\n[link] Route Map -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.102, 0.145, 0.152] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check all available tickets within $100 to $200 for the New York Knicks first game on April2 nd.\nPrevious actions:\n[link] sports. -> CLICK\n[textbox] Search by Name -> TYPE: New york knicks\n[p] New York Knicks -> CLICK\n[link] View Tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.909, 0.194, 0.991, 0.229] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a price quote for new Kia Carnival for 11101.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Free Dealer Price Quote -> CLICK\n[select] Make -> SELECT: Kia\n[select] Model -> SELECT: Carnival\n[textbox] ZIP -> TYPE: 11101" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.728, 0.136, 0.947, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the recent trades\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.32, 0.006, 0.393, 0.024] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[searchbox] From -> TYPE: brooklyn\n[listitem] Brooklyn, NY, USA -> CLICK\n[searchbox] To -> TYPE: staten island" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.325, 0.359, 0.348] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the new arrival of kids graphic t-shirt for 13 years old boy\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.006, 0.31, 0.044] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.035, 0.053, 0.082, 0.076] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find schedule for Long Island Rail Road & Metro-North Railroad from Bay Shore to Breakneck Ridge on Thu, Mar 23, 08:37 AM.\nPrevious actions:\n[link] Schedules -> CLICK\n[searchbox] From -> TYPE: Bay Shore\n[listitem] Bay Shore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.391, 0.474, 0.432] in the image\nAnd my action is Action: TYPE\nValue: Breakneck ridge" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly parking with valet service at the New York University.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York University\n[li] New York University, New York, NY, USA -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.373, 0.339, 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: What is the purchase price for powerwalls to install in a 200sqr feet 2 story house in the address 7528 East Mechanic Ave.Fargo, ND 58102\nPrevious actions:\n[link] Powerwall -> CLICK\n[link] Order Now -> CLICK\n[textbox] Shipping Address -> TYPE: 7528 East Mechanic Ave. Fargo, ND 58102\n[textbox] Shipping Address -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.747, 0.599, 0.861, 0.617] 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 best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: colombo\n[strong] Colombo -> CLICK\n[textbox] To 2180 results are available, use up and down arr... -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.466, 0.72, 0.506] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[button] Marketplace -> CLICK\n[link] Pop Rock -> CLICK\n[link] 958,222 United Kingdom -> CLICK\n[link] 246,685 CD -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.405, 0.163, 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: Buy the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[button] Sort: Recently Added -> CLICK\n[link] Price (lowest first) -> CLICK\n[button] Add Filter -> CLICK\n[link] Ship Location -> CLICK\n[button] Ship Location: Any -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.391, 0.168, 0.535, 0.181] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[span] Flights + Cruise -> CLICK\n[button] Search flights + cruise External Link should open ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.143, 0.968, 0.154] in the image\nAnd my action is Action: TYPE\nValue: ATLANTA" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for a group at Hurricane harbor Phoenix on April 22\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.573, 0.846, 0.61] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\n[link] SCHEDULES -> CLICK\n[input] -> TYPE: chicago\n[option] Chicago, IL - Union Station (CHI) -> CLICK\n[input] -> TYPE: los angeles" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.374, 0.128, 0.553, 0.165] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[img] Phil Collins - No Jacket Required -> CLICK\n[button] Add to List -> CLICK\n[combobox] List -> SELECT: New\n[button] Save -> CLICK\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.09, 0.188, 0.106] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check ticket listing on floor B row 17 seat listing to Beyoncé music concert on Mon Aug 14 at 7:00pm.\nPrevious actions:\n[link] Music -> HOVER\n[a] Trending -> HOVER\n[link] Beyonce -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.157, 0.183, 0.255, 0.2] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most recently posted job opening in customer service in Ireland with a remote working option.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.572, 0.796, 0.606, 0.803] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of BGG shirts for sale\nPrevious actions:\n[button] Shopping -> CLICK\n[link] BGG Store -> CLICK\n[link] Clothing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.102, 0.233, 0.115] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Kitchen -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.38, 0.197, 0.561, 0.229] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[input] -> TYPE: [email protected]\n[input] -> TYPE: Anderson\n[input] -> TYPE: po box 2846\n[input] -> TYPE: Texas\n[button] Complete -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.551, 0.231, 0.664, 0.247] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.061, 0.191, 0.082] in the image\nAnd my action is Action: TYPE\nValue: 25504" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[span] (Business/First) -> CLICK\n[button] Confirm -> CLICK\n[button] Show flights -> CLICK\n[heading] LKR 1,120,521 -> CLICK\n[button] Select fare -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.35, 0.727, 0.506] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mattresses available with Amazon Basics and Follow the store.\nPrevious actions:\n[link] Amazon Basics -> CLICK\n[link] BEDROOM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.231, 0.301, 0.4, 0.32] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recently added guitar pro non-acoustic tab intros\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Non-acoustic 1,805,658 -> CLICK\n[link] Intro 65,171 -> CLICK\n[link] Guitar Pro -> CLICK\n[div] Today's most popular -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.825, 0.428, 0.97, 0.457] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a gaming pc which can run Call of Duty Warzone at 4k.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.642, 0.207, 0.72, 0.219] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule between New York and Washington DC sorted by shortest trip.\nPrevious actions:\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] Depart Date -> CLICK\n[gridcell] Monday, April 17, 2023 -> CLICK\n[button] FIND TRAINS -> CLICK\n[span] Sort/Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.738, 0.388, 0.944, 0.403] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 map for the KCCR airport\nPrevious actions:\n[input] -> CLICK\n[input] -> TYPE: KCCR\n[option]  Buchanan Fld (Concord)  KCCR CCR   -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.353, 0.112, 0.45, 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 lowest rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[button] Date -> CLICK\n[button] 03/30/2023 -> CLICK\n[button] Browse Vehicles -> CLICK\n[checkbox] Trucks -> CLICK\n[combobox] SORT BY -> SELECT: Low to High" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.26, 0.059, 0.275] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open my item inventory.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.412, 0.0, 0.519, 0.03] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.693, 0.054, 0.727, 0.067] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[link] Careers -> CLICK\n[link] here -> CLICK\n[checkbox] Engineering (41 items) -> CLICK\n[checkbox] Spain (18 items) -> CLICK\n[checkbox] Madrid (2 items) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.547, 0.415, 0.563] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reviews of top critics for lowest rated Tom Hanks work\nPrevious actions:\n[textbox] Search -> TYPE: Tom Hanks" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.61, 0.704, 0.661] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow one of the team leaders of one of the NHL teams from the Atlantic Division\nPrevious actions:\n[link] ESPN NHL Home Page -> HOVER\n[link] Teams -> CLICK\n[heading] Boston Bruins -> CLICK\n[link] Full Team Statistics -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.338, 0.223, 0.391] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[tab] Rail Passes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.064, 0.498, 0.299, 0.518] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Paint -> CLICK\n[link] Painting Tools -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.017, 0.345, 0.028] in the image\nAnd my action is Action: TYPE\nValue: 44240" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 queen-size pillow protectors from the Marriot shop, and if found, add two pieces to the cart and checkout.\nPrevious actions:\n[button] Special Offers -> CLICK\n[link] Shop Marriott Opens a new window -> CLICK\n[menuitem] category pillows -> CLICK\n[span] Pillow Protector -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.69, 0.432, 0.838, 0.47] in the image\nAnd my action is Action: SELECT\nValue: Queen" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 amtrak national route map\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.032, 0.139, 0.065] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 spaces near Warner Theatre in Washington DC.\nPrevious actions:\n[link] CITIES -> CLICK\n[heading] WASHINGTON DC -> CLICK\n[link] Theaters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.146, 0.484, 0.375, 0.51] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.456, 0.284, 0.49] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: belo horizonte\n[div] Belo Horizonte, Minas Gerais, Brazil -> CLICK\n[tab] Flexible dates -> CLICK\n[label] Weekend -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.292, 0.151, 0.388, 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: search for art galleries in midtown\nPrevious actions:\n[link] attractions. -> CLICK\n[li] Neighborhood -> CLICK\n[link] Midtown -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.267, 0.218, 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 a comedy movie streaming on Netflix and add to watchlist.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.081, 0.587, 0.09] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 page with download options for fantasy apps.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.048, 0.14, 0.054] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Mens -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.241, 0.233, 0.265] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: sell playstation controller for cash credit on GameStop in 43240.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[img] -> CLICK\n[link] Sony DUALSHOCK 4 Wireless Controller for PlayStati... -> CLICK\n[div] Find a Store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.349, 0.76, 0.357] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find 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[button] Color -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Material -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.969, 0.021, 0.981, 0.035] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check car toll rate for bridges and tunnels\nPrevious actions:\n[span] Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.392, 0.234, 0.433] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of most popular upcoming game releases.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.22, 0.059, 0.31, 0.065] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: belo horizonte\n[div] Belo Horizonte, Minas Gerais, Brazil -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.167, 0.613, 0.19] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find climbing gear and sort the results by price high to low.\nPrevious actions:\n[button] Climb -> CLICK\n[button] Climb -> CLICK\n[link] Explore Climb -> CLICK\n[link] Shop all climbing gear -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.247, 0.381, 0.428, 0.409] in the image\nAnd my action is Action: SELECT\nValue: Price High - Low" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[link] Tickets, Passes, VIP Tours  -> CLICK\n[link] Group Tickets -> CLICK\n[i] -> CLICK\n[button] Buy Tickets -> CLICK\n[button] April 30, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.401, 0.054, 0.464, 0.07] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Delete the history of what i heard recently.\nPrevious actions:\n[link] Library -> CLICK\n[link] History -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.647, 0.093, 0.721, 0.106] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hard side Carry-on Luggage used for business in black color.\nPrevious actions:\n[link] Categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.269, 0.316, 0.311] in the image\nAnd my action is Action: CLICK" } ]