ejhshen/skill-alpha

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

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

Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

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

[EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

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

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.

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents