Tagged articles

SafeEvolve

2 articles · Page 1 of 1

Sep 17, 2026 · Artificial Intelligence

Beyond Prompts: Harness-Policy Co-Evolution for Agent Safety by Shanghai AI Lab

Shanghai AI Lab and university collaborators propose SHE and SafeEvolve, two frameworks that evolve agent safety by learning from execution trajectories: SHE updates a modular safety harness via trajectory-driven evolution, while SafeEvolve distills verified harness experience into the policy model through SFT and RL, reducing attack success rates on benchmarks.

Agent SafetyHarness EvolutionLLM agents

0 likes · 12 min read

Beyond Prompts: Harness-Policy Co-Evolution for Agent Safety by Shanghai AI Lab

Machine Learning Algorithms & Natural Language Processing

Sep 12, 2026 · Artificial Intelligence

SafeEvolve: Co-Evolving Harness and Policy for Self-Improving Agent Safety

SafeEvolve introduces a co-evolution framework where Agent Harness and Policy jointly learn from execution trajectories, reducing attack success rates to 0.79% on AgentDojo and 2.42% on Qwen3-4B while improving task utility, enabling continuous safety improvement from real-world experience.

AI SafetyAgent SafetyHarness-Policy Co-Evolution

0 likes · 9 min read

SafeEvolve: Co-Evolving Harness and Policy for Self-Improving Agent Safety