SkillClaw introduces collective skill evolution for multi-user LLM agents by processing aggregated trajectories with an autonomous evolver to update a shared skill repository, yielding performance gains for Qwen3-Max on WildClawBench.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
SkillClaw introduces collective skill evolution for multi-user LLM agents by processing aggregated trajectories with an autonomous evolver to update a shared skill repository, yielding performance gains for Qwen3-Max on WildClawBench.