一作ACL 2026Findings· Findings of ACL
O nto G uard: Enforcing Action Admissibility for LLM Agents in Complex Interactive Environments
Pengxiang Liu · Tao Ren · Wei Xiong · Tingrui Yang · Junjie Wang · Jun HU
摘要
Large Language Models (LLMs) have shown impressive reasoning capabilities in agents for complex interactive environments. However, these agents often suffer from hallucinations and lack grounding, leading to unreliable actions that conflict with real-world constraints. Existing approaches mitigat...