SkillOS: Learning Skill Curation for Self-Evolving Agents

ArXi:2605.06614v1 Announce Type: cross LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existing approaches either rely on manual skill curation, prescribe heuristic skill operations, or train for short-horizon skill operations. However, they still struggle to recipe for learning skill curation in self-evolving agents.