Self-Evolving Agent Harness: Scaffold Self-Improvement with Frozen Model Weights

Formalizes harness self-evolution, where an agent's scaffolding (prompts, memory, workflows, executable components) improves across runs while model weights stay frozen, with a framework separating update targets from proposal and admission mechanisms. It derives an expected generalization bound via continual PAC-learning and a high-probability admission rule gating revision acceptance with fresh validation data.