1
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
新基准SkillsBench，系统评估AI Agent技能在不同任务间的通用性与迁移能力，为智能体研究提供重要参考。
arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LL…