Preprint
Aug 2026
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Safety Harness Evolution (SHE) is proposed, a framework that learns evolving safe boundaries from rollout trajectories and introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through safety-utility validation.
Wanying Qu, Qinghua Mao, Yu Li et al.
· 1 citation