SOURCE-LINKED INTELLIGENCE

SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmful final responses and multi-step execution trajectories. Existing safety alignment mechanisms often rely on either external harness updates or policy optimization, yet applying either paradigm in isolation fails to bridge runtime control with intrinsic safety. We propose SafeEvolve, an experience-driven self-evolving framework for agent safety alignment. SafeEvolve leverages safety experience from completed on-policy

Read original source ↗ Open in workspace

recordType

paper

region

Global