@inproceedings{liu-etal-2026-ontoguard,
    title = "{O}nto{G}uard: Enforcing Action Admissibility for {LLM} Agents in Complex Interactive Environments",
    author = "Liu, Pengxiang  and
      Ren, Tao  and
      Xiong, Wei  and
      Yang, Tingrui  and
      Wang, Junjie  and
      HU, Jun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1051/",
    pages = "20937--20952",
    ISBN = "979-8-89176-395-1",
    abstract = "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 mitigate some issues through implicit imitation or sparse reinforcement learning but rely on fitting data distributions without explicitly understanding environmental constraints, often generating actions that are behaviorally distorted or environmentally impermissible. To address this, we introduce OntoGuard, an ontological framework designed to guard LLM agents by enforcing environmental and behavioral admissibility. These constraints are constructed by extracting knowledge from oracle demonstrations, supplemented with world knowledge inherent in LLMs and general knowledge bases. During inference, OntoGuard functions as an active interceptor, using a graph-based constraint-checking mechanism to reject invalid actions and prompt self-correction before acting. Experiments on both ScienceWorld and VirtualHome demonstrate OntoGuard{'}s advantage over state-of-the-art methods, validating its ability to enforce physical and behavioral constraints while preventing invalid actions."
}