arXivNahyun Lee, Dongkeun Yoon, Guijin Son, Geewook Kim, Dayoon Ko, Jeonghun Park, Haneul Yoo, Jaewon Cho, Junghun Park, Changyoon Lee, Kyochul Jang, Jaeyeon Kim, Eunsu Kim, Woojin Cho, Seungone KimMon, Jun 1, 2026, 8:50 AM PDT
score 16.5
New benchmark reveals AI agents struggle with Korean web tasks
Original: K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Source: arxiv.org ↗
Writing ELI5 summary…