arXivJinyi Han, Yuanjian Xu, Ying Liao, Xinyi Wang, Zishang Jiang, Zixiang Di, Fanyang Lu, Zhichao Hu, Yanghua XiaoWed, Aug 5, 2026, 6:29 AM PDT
score 17.1
AI agents struggle to actually use their skills, new benchmark finds
Original: Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?
Source: arxiv.org ↗
Writing ELI5 summary…