用因果关系提升多人游戏智能体协作效率
CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
- 引入任务图与因果模块管理多智能体依赖关系
- 在Minecraft协作任务中达到当前最佳表现
- 适合研究多智能体协同与因果推理的学者
Minecraft作为开放世界虚拟交互环境，已成为智能体决策与执行研究的重要平台。现有方法多采用单一大语言模型智能体完成各类游戏任务，但在需要长序列动作的复杂任务中，常面临效率低和容错性差的问题。尽管如此，多智能体协作研究仍十分有限。本文提出CausalMACE，一种全面融合因果推理的多智能体协作框架，通过引入因果机制管理子任务间的依赖关系。技术上，该框架包含全局任务图用于整体规划，以及基于因果的依赖管理模块，利用内在规则实施因果干预。实验结果表明，该方法在Minecraft多智能体协作任务中达到了当前最优性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。