@inproceedings{fan-etal-2026-leibniz,
    title = "Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration",
    author = "Fan, Yue  and
      Zhang, Hu  and
      Zhao, Yunxiao  and
      Zhang, Guangjun  and
      Zhan, Hao  and
      Li, Ru  and
      Tan, Hongye  and
      Wang, Yuanlong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.924/",
    pages = "20186--20210",
    ISBN = "979-8-89176-390-6",
    abstract = "Logical reasoning with large language models (LLMs) has made significant progress in recent years. However, existing methods still suffer from insufficient rule semantic grounding and weak rule application mechanisms, making it difficult to achieve precise understanding and effective utilization of rules in complex multi-step reasoning. To address this, we propose Leibniz, a theory-of-mind driven neuro-symbolic reasoning framework. Specifically, we construct a bidirectional reasoning model based on multi-agent collaboration, which characterizes the reasoning process from two complementary perspectives, namely the Evolution Agent and the Reduction Agent. The former transforms belief-unstable propositions into stable ones that are beneficial for proving the target conclusion. The latter performs reverse reduction from the target to resolve belief conflicts and distill new inferential insights. Both share a belief state space and achieve efficient collaborative reasoning through continual belief updating. We integrate natural language and symbolic representations throughout the reasoning process. The experimental results demonstrate that Leibniz surpasses existing state-of-the-art models in reasoning accuracy, and further analyses reveal its substantial advantages in reliability and flexibility."
}