Gate every auto-created agent skill behind unit tests and runtime feedback (MUSE-Autoskill)

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation (arXiv 2605.27366)·medium signal

MUSE-Autoskill (May 2026) formalizes a full skill lifecycle — creation, memory, management, evaluation, refinement — where agents create skills on demand and, critically, evaluate each one with unit tests and runtime feedback before reuse, plus skill-level memory that accumulates experience per skill across tasks. This adds a verification gate that prevents a self-improving agent from poisoning its own library with brittle or wrong skills. Pair it with hierarchical consolidation for a self-evolving setup that grows without rotting.