Yutao Mou

Current safety alignment techniques for large language models (LLMs) struggle to balance harmlessness and helpfulness: improving safety often comes at the cost of degraded utility. Our preliminary study shows that guiding unaligned base models with safety-aware reasoning that includes explicit se...

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before unsafe execution is critical for agent deployment, yet remain...