@inproceedings{xu-zhong-2025-comet,
    title = "{C}o{M}et: Metaphor-Driven Covert Communication for Multi-Agent Language Games",
    author = "Xu, Shuhang  and
      Zhong, Fangwei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.acl-long.389/",
    doi = "10.18653/v1/2025.acl-long.389",
    pages = "7892--7917",
    ISBN = "979-8-89176-251-0",
    abstract = "Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain. However, many large language models (LLMs) struggle to interpret and apply metaphors in multi-agent language games, hindering their ability to engage in covert communication and semantic evasion, which are crucial for strategic communication. To address this challenge, we introduce CoMet, a framework that enables LLM-based agents to engage in metaphor processing. CoMet combines a hypothesis-based metaphor reasoner with a metaphor generator that improves through self-reflection and knowledge integration. This enhances the agents' ability to interpret and apply metaphors, improving the strategic and nuanced quality of their interactions. We evaluate CoMet on two multi-agent language games{---}Undercover and Adversarial Taboo{---}which emphasize ``covert communication'' and ``semantic evasion''. Experimental results demonstrate that CoMet significantly enhances the agents' ability to communicate strategically using metaphors."
}