CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

TL;DR

CausalMACE introduces a causality-based planning framework that significantly improves multi-agent cooperation in Minecraft by managing task dependencies and enhancing efficiency in complex, multi-step tasks.

Contribution

It presents a novel causality-aware multi-agent framework with task graph planning and causal intervention, addressing limitations of single-agent approaches.

Findings

Achieves state-of-the-art performance in Minecraft cooperative tasks.

Enhances efficiency and fault tolerance in multi-agent collaboration.

Effectively manages task dependencies through causal intervention.

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.