@inproceedings{mou-etal-2025-ecolang,
    title = "{E}co{LANG}: Efficient and Effective Agent Communication Language Induction for Social Simulation",
    author = "Mou, Xinyi  and
      Qian, Chen  and
      Liu, Wei  and
      Yan, Ling  and
      Hu, Yao  and
      Huang, Xuanjing  and
      Wei, Zhongyu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.284/",
    doi = "10.18653/v1/2025.findings-emnlp.284",
    pages = "5287--5304",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) have demonstrated an impressive ability to role-play humans and replicate complex social dynamics. However, large-scale LLM-driven simulations still face significant challenges in high time and computational costs. We observe that there exists redundancy in current agent communication: when expressing the same intention, agents tend to use lengthy and repetitive language, whereas humans naturally prefer concise expressions. To this end, we propose EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation. Inspired by how human language evolves through interactions, we induce a more compact language by identifying and preserving core communicative concepts at the vocabulary level and evolving efficient expression patterns at the sentence level through natural selection. We apply the induced language in various social simulations. Experimental results demonstrate that EcoLANG reduces token consumption by over 20{\%}, enhancing efficiency without sacrificing simulation accuracy."
}