Skill-evolution — Topic

📑 arXiv 5d ago

SkillClaw: LLM Agent Skills Evolve Through Collective Cross-User Experiences

SkillClaw enables LLM agent skills to evolve autonomously by aggregating interaction experiences across users, with an 'agentic evolver' that refines capabilities from real-world usage. Achieves +42.1% improvement by shifting from static, manually-engineered skills to continuously improving ones learned from collective deployment data.

Agents Continual-learning Skill-evolution

📑 arXiv 1w ago

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

SkillClaw enables collective skill evolution across multi-user LLM agent ecosystems by continuously aggregating interaction trajectories and autonomously refining skills via an agentic evolver, achieving 88% improvement after 6 rounds and +42.1% on real-world tasks. It enables cross-user knowledge transfer without additional user effort, solving the inefficiency where users repeatedly develop similar workflows independently.

Agents Learning-systems Skill-evolution Multi-user

SkillClaw: LLM Agent Skills Evolve Through Collective Cross-User Experiences ↗

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver ↗

SkillClaw: LLM Agent Skills Evolve Through Collective Cross-User Experiences

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver