Saved in:
Bibliographic Details
Main Authors: Chai, Qi, Zheng, Zhang, Ren, Junlong, Ye, Deheng, Lin, Zichuan, Wang, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.18797
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.