Skip to main content
Search

Dongrui Liu

1 related articles

Subscribe to updates
  1. arXiv

    Agent safety harnesses stop freezing at deployment: SHE learns boundaries from rollout trajectories and cuts attack success to 5.5%

    A team at Shanghai Artificial Intelligence Laboratory and collaborators turned the safety harness of large language model agents from a fixed deployment artifact into an evolvable object: the harness is split into four editable artifacts, a system prompt, rule bank, safety memory and tool policy, and failures in rollout trajectories are diagnosed and routed to the responsible artifact for local revision. On Agent-SafetyBench the evolved harness lowers average attack success rate from 17.1% for the static SafeHarness to 5.5% while raising utility under attack from 31.6% to 47.6%. The evolved harness also lowers the Harm Score on the held-out AgentHarm from 19.8% to 9.8%.

You’re all caught up