@inproceedings{chai-etal-2025-causalmace,
    title = "{C}ausal{MACE}: Causality Empowered Multi-Agents in {M}inecraft Cooperative Tasks",
    author = "Chai, Qi  and
      Zheng, Zhang  and
      Ren, Junlong  and
      Ye, Deheng  and
      Lin, Zichuan  and
      Wang, Hao",
    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.777/",
    doi = "10.18653/v1/2025.findings-emnlp.777",
    pages = "14410--14426",
    ISBN = "979-8-89176-335-7",
    abstract = "Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various in-game tasks. However, for complex tasks requiring lengthy sequences of actions, single-agent approaches often face challenges related to inefficiency and limited fault tolerance. Despite these issues, research on multi-agent collaboration remains scarce. In this paper, we propose CausalMACE, a holistic causality planning framework designed to enhance multi-agent systems, in which we incorporate causality to manage dependencies among subtasks. Technically, our proposed framework introduces two modules: an overarching task graph for global task planning and a causality-based module for dependency management, where inherent rules are adopted to perform causal intervention. Experimental results demonstrate our approach achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft. The code will be open-sourced upon the acceptance of this paper."
}