SkillFocus: Evolving Agent Skills via Capability Decomposition
Agent skill evolution seeks to improve reusable procedural guidance for large language model (LLM) agents through iterative revision. Existing methods base each revision mainly on execution trajectories or feedback, leaving recurring behavioral requirements across tasks implicit and tying revision to the behavior of th...
Ning Wang, Z. Gong, Bing-Dong Li et al.
· 0 citations