aworld_visualwebarena_tr

# Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution ## json format ``` { "0": { "info": { "fail_error": "", "observation_metadata": { "text": { "url": "obs_nodes_info": , "tabs": }, "image": { "obs_nodes_info": { } } }, "intent": , "input_images": , "ss_ori": , "ss_som": }, "action": { # same with visualwebarena dataset "action_type": , "coords": [ 0.0, 0.0 ], "element_role": 0, "element_name": "", "text": [], "page_number": 0, "url": "", "nth": 0, "pw_code": "", "element_id": "", "key_comb": "", "direction": "", "answer": , "raw_prediction": , "action_info": { "pred_action_history": "", "pred_action_description": "", "pred_action": "", "pred_action_type": "", "pred_bbox": "", "pred_type_value": "", "pred_click_point": "", "parse_error_msg": "", "content_to_memo": "" } } } } ``` action_type see the codes below: ``` class ActionTypes(IntEnum): """Valid action types for browser env.""" NONE = 0 # mouse wheel and keyboard, universal across all action spaces SCROLL = 1 KEY_PRESS = 2 # low level mouse and keyboard actions MOUSE_CLICK = 3 KEYBOARD_TYPE = 4 MOUSE_HOVER = 5 # mid level mouse and keyboard actions CLICK = 6 TYPE = 7 HOVER = 8 # page level actions, universal across all action spaces PAGE_FOCUS = 9 NEW_TAB = 10 GO_BACK = 11 GO_FORWARD = 12 GOTO_URL = 13 PAGE_CLOSE = 14 # high-leval actions that playwright support CHECK = 15 SELECT_OPTION = 16 STOP = 17 CLEAR = 18 UPLOAD = 19 WAIT = 20 DRAG = 21 ```Recon-Act：一种依托网页侦察、工具生成与任务执行的自进化多智能体（Multi-Agent）浏览器使用系统