Preprint
Aug 2026
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback
Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause. Recent work does close this loop, but derives its feedback from single-turn question-answering evaluation....
Qian-Xi Yan, Chun-Rong Chen, Jiu-Zhou Zhao et al.
· 0 citations