VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails

Summary

VEPA is a framework that evolves formal agent guardrails during deployment. An LLM proposes policy patches as executable symbolic rules over typed agent events, a deterministic verifier accepts only structurally valid, conflict-free policies, and an evidence-aware layer activates rules only with enough supporting evidence. Across ASSEBench-Safety, ASSEBench-Security, and ATBench, it outperforms baselines and keeps working under mixed streams, corrupted feedback, and longer horizons.