作者位次 #6/10ACL 2026Poster· Natural Language Processing
S afe A gent: Safeguarding LLM Agents via an Automated Risk Simulator
Xueyang Zhou · Weidong Wang · Lin Lu · Jiawen Shi · Guiyao Tie · Xu Yongtian · Lixing Chen · Pan Zhou · Neil Zhenqiang Gong · Lichao Sun
摘要
LLM-based agents are rapidly being deployed in real-world applications (e.g., digital assistants and customer service), making safety a critical concern. However, in multi-turn, tool-augmented settings, dynamic user interactions, external tool use, and unintended harmful behaviors make robust saf...