8 Commits

Author	SHA1	Message	Date
yuanmengqi	6f0382c0c2	Merge branch 'main' of github.com:xlang-ai/OSWorld	2025-07-10 22:35:42 +00:00
yuanmengqi	6897e5320d	Enhance image text comparison functionality with detailed logging ... - Added logging for OCR results and text matching outcomes in compare_image_text function. - Updated JSON examples to support multiple expected results and improved structure for evaluator functions. - Enhanced handling of expected text rules to include multiple variations for better matching accuracy.	2025-07-10 22:32:53 +00:00
st2rb8g	61f265a082	fix some multi_apps tasks (#245) ... * fix chrome * fix some multi_apps tasks. * fix some multiapps tasks * fix some multiapps tasks --------- Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>	2025-07-11 06:32:13 +08:00
Timothyxxx	fb7bafb885	feat: Add proxy configuration to all 369 evaluation examples - 55 with proxy, 314 without	2025-06-05 18:46:53 +08:00
Timothyxxx	34748567a5	feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation ... - Add detailed README for file cache repository - Implement migration script with retry logic and browser simulation - Support automatic file type detection and deduplication - Ensure reliable hosting for OSWorld evaluation files	2025-05-28 04:29:37 +08:00
Jason Lee	775cef744f	xiaochuan correct his bugs in multiapp examples, you can try it again now	2024-03-10 14:48:56 +08:00
Jason Lee	2291af394f	update google drive file link in json	2024-03-09 18:06:48 +08:00
Jason Lee	62fd8feebb	xiaochuan's multiapp examples	2024-03-08 19:24:15 +08:00