Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 84

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: JFK\n[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[textbox] Depart , required. -> TYPE: 04/23/2023\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.238, 0.357, 0.26] in the image\nAnd my action is Action: SELECT\nValue: Total travel time" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Tokyo's best tea related attractions in the morning.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.03, 0.274, 0.056] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used women's running shoes available in a size 5\nPrevious actions:\n[menuitem] Women's -> CLICK\n[menuitem] Running Shoes -> CLICK\n[label] 5 (10) -> CLICK\n[combobox] Sort By: -> SELECT: Price: Low - High\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.286, 0.523, 0.301] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\n[searchbox] Search -> TYPE: SOUTH AFRICAN HISTORY PODCAST\n[button] Search -> CLICK\n[link] Tracks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.198, 0.212, 0.21] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the list of ballet event for the next 30 days.\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: Ballet\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.547, 0.18, 0.569, 0.198] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events in Los Angeles and select the one on the Friday this weekend.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.036, 0.464, 0.066] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my trip with ticket number 3329456534543 along with my name John Green\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[combobox] Find Your Trip By -> CLICK\n[option] Ticket Number -> CLICK\n[input] -> TYPE: 3329456534543\n[input] -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.068, 0.851, 0.092] in the image\nAnd my action is Action: TYPE\nValue: Green" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Alfred\n[span] Alfred, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.212, 0.721, 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: Order popcorn at AMC Grove City 14\nPrevious actions:\n[link] Order Food & Drinks -> CLICK\n[select] AMC Columbus 10 -> SELECT: AMC Grove City 14\n[button] Order Now -> CLICK\n[img] -> CLICK\n[button] Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.426, 0.195, 0.562, 0.239] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the season pass prices for Hurricane HarborLos Angeles.\nPrevious actions:\n[span] Hurricane Harbor Los Angeles -> CLICK\n[button] Go! -> CLICK\n[link] Tickets & Passes  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.102, 0.468, 0.114] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SkyMiles domestic Award Deals from Philadelphia to Atlanta.\nPrevious actions:\n[tab] SkyMiles -> CLICK\n[link] SkyMiles Award Deals -> CLICK\n[combobox] Origin -> CLICK\n[option] PHL Philadelphia, PA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.357, 0.496, 0.643, 0.528] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an outdoor table for 3 people at a Los Angeles restaurant for 5:00 PM on April 7th\nPrevious actions:\n[button] Los Angeles -> CLICK\n[link] La Cha Cha Cha -> CLICK\n[div] Today -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.377, 0.203, 0.408, 0.227] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track an order using the order number of 456481897 and phone number of 8984486417.\nPrevious actions:\n[link] Order Tracker -> CLICK\n[textbox] Order number EXAMPLES: ECEA12345, 01234567 -> TYPE: 456481897\n[textbox] Email or Phone Number (associated with Order) -> TYPE: 898-448-6474" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.913, 0.241, 0.99, 0.27] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for wall art with a price range of $25 to $50.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: wall art\n[input] -> CLICK\n[link] Wall Art -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.46, 0.168, 0.481] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[button] Ohio United States -> CLICK\n[button] Check-in March 18, 2023 -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.701, 0.193, 0.743, 0.213] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movies produced by Aaron Horvath.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.189, 0.005, 0.613, 0.017] in the image\nAnd my action is Action: TYPE\nValue: Aaron Horvath" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[textbox] Guest rooms -> TYPE: 7\n[textbox] Event space -> TYPE: 50\n[button] Find -> CLICK\n[generic] Brand -> CLICK\n[generic]  The Ritz-Carlton (4) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.86, 0.285, 0.96, 0.318] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 book by Sam Harris that has a rating of at least 4 stars and is available in paperback format.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Sam Harris\n[button] sam harris -> CLICK\n[region] 4 Stars & Up -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.227, 0.068, 0.235] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the monthly payment of a 15k car with a down payment of 5k in Michigan for a fair-rated person for a term length of 48 months, then shop with this budget for the cheapest car and add it to the favorites.\nPrevious actions:\n[link] Car payment calculator -> CLICK\n[textbox] Vehicle Price -> TYPE: 15000\n[textbox] Down Payment -> TYPE: 5000\n[combobox] State -> SELECT: Michigan\n[combobox] Credit Score -> SELECT: Fair (580-669 FICO® Score)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.314, 0.459, 0.337] in the image\nAnd my action is Action: SELECT\nValue: 48 months" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: GOA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.339, 0.409, 0.385] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest news about Mikal Bridges\nPrevious actions:\n[button] Open Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.034, 0.931, 0.054] in the image\nAnd my action is Action: TYPE\nValue: Mikal Bridges" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Boston Logan Airport to North Station.\nPrevious actions:\n[tab] Trip Planner -> CLICK\n[combobox] From -> TYPE: Boston Logan Airport\n[option] Boston Logan Int'l Airport, 1 Harborside Dr, East ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.544, 0.205, 0.807, 0.229] in the image\nAnd my action is Action: TYPE\nValue: North Station" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[checkbox] 19 inch (7) -> CLICK\n[button] Sort By: Best Match -> CLICK\n[button] Price Low to High -> CLICK\n[generic] Click to add item \"Tuscany® Baytown Drop-In 33\" St... -> CLICK\n[generic] Click to add item \"Dayton Drop-In 25\" Stainless St... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.419, 0.958, 0.434] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[combobox] Infant 1 age -> SELECT: Under 1\n[button] Done -> CLICK\n[button] Preferred flight class Economy -> CLICK\n[menuitem] First class -> CLICK\n[button] Departing April 5, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.953, 0.339, 0.995, 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: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: 66 perry st\n[span] 66 -> CLICK\n[span] Apr 18 -> CLICK\n[gridcell] 20 -> CLICK\n[span] 01:30PM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.635, 1.083, 0.758, 1.11] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[span] Any -> CLICK\n[li] -> CLICK\n[spinbutton] Max Price -> TYPE: 75\n[span] mm/dd/yyyy-mm/dd/yyyy -> CLICK\n[Abbr] May 7, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.393, 0.312, 0.422] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] 3/25/2023 -> CLICK\n[link] 25, Saturday March 2023 -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Rail -> CLICK\n[label] Express Bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.396, 0.386, 0.848, 0.419] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[link] BABY -> HOVER\n[tab] Toddler (6M-5Y) -> CLICK\n[link] All Toddler (6M-5Y) -> CLICK\n[heading] Category -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.061, 0.459, 0.47, 0.476] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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: 252-654-5258\n[input] -> TYPE: [email protected]\n[input] -> TYPE: Anderson\n[input] -> TYPE: po box 2846\n[input] -> TYPE: Texas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.147, 0.773, 0.162] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 crossbows on sale with limited stock.\nPrevious actions:\n[link] Hunting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.206, 0.206, 0.217] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[div] Durban -> CLICK\n[link] Discover -> CLICK\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: doha\n[strong] Doha -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.426, 0.451, 0.481, 0.472] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recently posted part-time Job in Gamestop stores in Fresno, California, and apply.\nPrevious actions:\n[span] -> CLICK\n[button] City -> CLICK\n[searchbox] City -> TYPE: fre\n[span] -> CLICK\n[button] Hiring Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.597, 0.13, 0.612] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the list of off-Broadway theatre shows on April 19\nPrevious actions:\n[button] THEATRE -> CLICK\n[link] Off-Broadway -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.72, 0.264, 0.881, 0.281] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the best VIP seat to the Red Hot Chili Peppers 2023 Tour\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER\n[link] Jazz -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.452, 0.953, 0.575] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[option] Brooklyn, NY, US Select -> CLICK\n[button] Selected Pick-Up Date 03/19/2023 -> CLICK\n[button] 04/05/2023 -> CLICK\n[svg] -> CLICK\n[button] 04/08/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.508, 0.84, 0.555] in the image\nAnd my action is Action: SELECT\nValue: 22" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 highest rated white water rafting experience available in Montana from May 1 to May 7\nPrevious actions:\n[textbox] Where to? -> TYPE: Montana\n[button] Montana USA -> CLICK\n[button] Next -> CLICK\n[gridcell] Mon May 01 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.519, 0.313, 0.556, 0.331] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the Emergency Sickness Plan policy certificates for Connecticut.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.032, 0.74, 0.048] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: MUMBAI\n[button] Mumbai, IN (BOM) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: LONDON\n[button] London, GB (LON - All Airports) -> CLICK\n[textbox] Depart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.513, 0.27, 0.543, 0.291] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[link] Selena Gomez -> CLICK\n[link] Popular tracks -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[a] Create a playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.092, 0.695, 0.105] in the image\nAnd my action is Action: TYPE\nValue: Love" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\n[link] Live TV -> CLICK\n[button] Broadcast TV Spokane (3) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.085, 0.773, 0.098] in the image\nAnd my action is Action: TYPE\nValue: 99201" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 results of the most recent NFL games.\nPrevious actions:\n[link] NFL . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.121, 0.062, 0.21, 0.068] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 with the least amount of walking from Central Park Zoo to the Broadway Theater.\nPrevious actions:\n[searchbox] From -> TYPE: central park zoo\n[listitem] Central Park Zoo, East 64th Street, New York, NY, ... -> CLICK\n[searchbox] To -> CLICK\n[searchbox] To -> TYPE: broadway\n[listitem] Broadway Theatre, Broadway, New York, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.248, 0.359, 0.268] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[textbox] Search -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.053, 0.005, 0.219, 0.028] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest event to attend in Athens, Greece on April 2nd\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.054, 0.546, 0.087] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the rating and user reviews for the game \"Deathloop\".\nPrevious actions:\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.168, 0.677, 0.197] in the image\nAnd my action is Action: TYPE\nValue: Deathloop" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information about how to buy metro card on booth.\nPrevious actions:\n[link] Fares & Tolls -> CLICK\n[div] Where to buy a MetroCard -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.258, 0.409, 0.742, 0.451] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Add 1 -> CLICK\n[button] Add 2 -> CLICK\n[button] Find Hotels -> CLICK\n[checkbox] Show rates with taxes and all fees -> CLICK\n[checkbox] Show available hotels only -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.255, 0.245, 0.377, 0.267] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[button]  -> CLICK\n[button]  -> CLICK\n[gridcell] Sun, Jun 4, 2023 -> CLICK\n[div] Start Date -> CLICK\n[button] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.274, 0.298, 0.803, 0.316] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.563, 0.444, 0.645, 0.468] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[textbox] To -> CLICK\n[button] Greece -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.209, 0.715, 0.225] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] Next -> CLICK\n[button] None -> CLICK\n[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.663, 0.284, 0.686] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[path] -> CLICK\n[span] Delivery -> CLICK\n[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.174, 0.734, 0.232] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox Series X|S -> CLICK\n[link] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.144, 0.375, 0.159] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[span] Marriott Deluxe Box -> CLICK\n[textbox] To -> TYPE: Clara\n[textbox] From -> TYPE: James\n[textbox] Message Line 1 -> TYPE: Happy Christmas\n[button] Add to Cart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.721, 0.616, 0.9, 0.639] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the winning odds in the Champions League for Real Madrid against Chelsea.\nPrevious actions:\n[span] Odds -> CLICK\n[heading] SOCCER -> CLICK\n[heading] ENGLISH PREMIER LEAGUE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.337, 0.375, 0.378] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy shows taking place in Chicago, IL and expand the results once.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: Chicago\n[option] Chicago, IL -> CLICK\n[button] See next Categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.748, 0.223, 0.965, 0.329] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[button] add Bottomless Bubbles to the cart with price $9.5... -> CLICK\n[div] I want to give a gift to a booked cruiser -> CLICK\n[textbox] first-name -> TYPE: Joe\n[textbox] last-name -> TYPE: Bloggs\n[textbox] booking-number -> TYPE: 101010" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.582, 0.23, 0.604] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\n[menuitem] Chicago United States of America ORD OHare Interna... -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: Paris\n[menuitem] Paris France CDG Charles De Gaulle Airport -> CLICK\n[option] One way -> CLICK\n[gridcell] 17 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.819, 0.288, 0.922, 0.33] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: Chicago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.287, 0.5, 0.35] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[span] Newegg -> CLICK\n[button] APPLY -> CLICK\n[span] Magenta -> CLICK\n[button] APPLY -> CLICK\n[span] Single Pack -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.136, 0.192, 0.148] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for flights available from Calgary (CYYC) to New York (ZNY).\nPrevious actions:\n[textbox] Origin -> TYPE: Calgary\n[div] Calgary -> CLICK\n[textbox] Destination -> TYPE: New York\n[strong] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.232, 0.639, 0.239] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gift shops available at a park in New York\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Darien Lake -> CLICK\n[button] Go! -> CLICK\n[link] Rides & Experiences  -> CLICK\n[link] Shops & Gifts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.204, 0.248, 0.218] in the image\nAnd my action is Action: SELECT\nValue: Gifts" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: albany" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.345, 0.153, 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 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.316, 0.384, 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: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[textbox] *First Name -> TYPE: John\n[textbox] *Last Name -> TYPE: Mark\n[textbox] *Email Address -> TYPE: [email protected]\n[textbox] *Phone Number -> TYPE: 234567890\n[label] I am NOT a Travel Advisor. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.131, 0.544, 0.168] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the balance for a gift card with the number 1000000000000000 and pin 1222\nPrevious actions:\n[link] Visit the Gift Cards page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.348, 0.74, 0.482, 0.779] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 black strollers within $100 to $250.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: black stroller\n[input] -> CLICK\n[div] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.329, 0.123, 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: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[menuitem] 2018 -> CLICK\n[button] 2023 -> CLICK\n[menuitem] 2022 -> CLICK\n[button] Back to all categories -> CLICK\n[button] Exterior Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.349, 0.249, 0.378] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[link] Jackets -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Jackets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.508, 0.233, 0.544] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $100 Google Play Gift Card to cart and recipient email address as [email protected]\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Google Play\n[button] google play gift card -> CLICK\n[img] Sponsored Ad - Google Play gift code - give the gi... -> CLICK\n[button] $100 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.321, 0.654, 0.336] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] 2+ -> CLICK\n[radio] Owned -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.512, 0.096, 0.536] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Change the language to UK English and the currency to Euros\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.452, 0.084, 0.653, 0.108] in the image\nAnd my action is Action: SELECT\nValue: 🇬🇧 English (UK)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a parking button code for my company Boston Legal located near Boston Navy Yard, and the button should be 160x400 pixels, and the parking spot should be within 15 miles of my address.\nPrevious actions:\n[link] ADD PARKING TO YOUR WEBSITE -> CLICK\n[textbox] STEP 1: Enter Your Company Name -> TYPE: BOSTON LEGAL\n[combobox] STEP 2:Enter an address to search and select a loc... -> TYPE: BOSTON NAVY YARD" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.566, 0.489, 0.59] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] 2 travelers -> CLICK\n[img] Increase children -> CLICK\n[img] Increase infants -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.568, 0.326, 0.7, 0.361] in the image\nAnd my action is Action: SELECT\nValue: 4" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find travel agents in Grand Junction, Colorado\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search the site -> TYPE: travel agent\n[button] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.192, 0.12, 0.662, 0.143] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals in New York.\nPrevious actions:\n[a] City Pages -> CLICK\n[link] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.72, 0.39, 0.858, 0.401] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated chords for the song La Bomba\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: La Bomba\n[button] SEARCH -> CLICK\n[link] Chords -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.909, 0.19, 0.971, 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: Find flights from Washington airports to New York airports and only show those with scheduled status.\nPrevious actions:\n[textbox] Origin -> TYPE: Washington\n[div] Washington -> CLICK\n[textbox] Destination -> TYPE: New York\n[div] New York -> CLICK\n[img] Submit Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.387, 0.205, 0.402] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details of Grand National Parks tour.\nPrevious actions:\n[button] DEALS -> CLICK\n[link] VACATIONS & RAIL TOURS Train vacation packages thr... -> CLICK\n[img] -> CLICK\n[link] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.202, 0.407, 0.284, 0.479] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[div] 10 -> CLICK\n[span] 12 -> CLICK\n[img] Add -> CLICK\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.456, 0.132, 0.574, 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: Show me the list of playstation 5 games available for pre-orders.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Video Games chevron_right -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.192, 0.291, 0.232] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 2 at a restaurant that was featured on the latest Hit List\nPrevious actions:\n[link] The Hit List -> CLICK\n[a] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.243, 0.356, 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: Show the Recommended Gaming PCs for someone who plays Fortnite, Overwatch and GTA V at 4k\nPrevious actions:\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK\n[div] Remove -> CLICK\n[div] Remove -> CLICK\n[p] Remove -> CLICK\n[button] 4K -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.319, 0.703, 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 a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.435, 0.061, 0.471, 0.069] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 retired players named James Smith\nPrevious actions:\n[link] Players -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.171, 0.737, 0.182] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 glamping locations in Northern California.\nPrevious actions:\n[link] WAYS TO STAY  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.132, 0.266, 0.15] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated dog collar under 10 dollar.\nPrevious actions:\n[link] Pet -> CLICK\n[span] Pet Type -> CLICK\n[link] Dog (1,338) -> CLICK\n[span] Category -> CLICK\n[link] Collars & Leashes (485) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.265, 0.986, 0.293] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] See railroad fare details. -> CLICK\n[link] Plan a trip to see fares. -> CLICK\n[searchbox] From -> TYPE: grand central\n[span] Grand Central -> CLICK\n[searchbox] To -> 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, 0.414] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car guide info for economy car and reserve.\nPrevious actions:\n[button] Cars & Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.057, 0.812, 0.083] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all time most popular solo track by ArianaGrande\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: Ariana Grande" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.953, 0.0, 1.0, 0.053] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Add Filter -> CLICK\n[link] Ship Location -> CLICK\n[button] Ship Location: Any -> CLICK\n[link] Canada -> CLICK\n[link] King of Tokyo -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.814, 0.142, 0.97, 0.173] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the artist profile of M S Subbulakshmi and play all from the top tracks.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: m s subbulakshmi" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.953, 0.0, 1.0, 0.029] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\n[link] Products -> CLICK\n[button] Bathroom -> CLICK\n[link] Bathroom storage -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: 60173" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.917, 0.124, 0.948, 0.157] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK\n[textbox] Vehicle Price -> CLICK\n[textbox] Vehicle Price -> TYPE: 10000\n[textbox] Down Payment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.301, 0.459, 0.332] in the image\nAnd my action is Action: TYPE\nValue: 500" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a large store in Washington that has kids' and maternity products, also check if they have a parking lot, and see the directions of the nearest store.\nPrevious actions:\n[input] -> CLICK\n[option] WA -> CLICK\n[button] Products -> CLICK\n[label] Kids -> CLICK\n[label] Maternity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.666, 0.412, 0.694] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[option] Los Angeles, CA - Union Station (LAX) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.576, 0.076, 0.672, 0.095] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a smartwatch to the cart that is compatible with an iPhone.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: smartwatch\n[button] smartwatches -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.528, 0.032, 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: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.063, 0.777, 0.077] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: london\n[span] London -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.068, 0.327, 0.084] in the image\nAnd my action is Action: TYPE\nValue: sheffield" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[textbox] From -> TYPE: new york\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: washington\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[div] Depart Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.792, 0.174, 0.805, 0.189] in the image\nAnd my action is Action: CLICK" } ]