Zhouyaner/EviSkill

[Findings of EMNLP 2026] Official implementation of SkillRevise: trace-conditioned revision of LLM-authored agent skills.

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification — COLM 2026

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

🥇 Not Just Another Agent Framework, But a Bayesian Evolution Layer That Can Work Across Harnesses

[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Let Skills Evolve Collectively with Agentic Evolver