CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
This addresses the problem of multi-agent collaboration in Minecraft for researchers, but it appears incremental as it builds on existing single-agent methods with causality enhancements.
The paper tackles the problem of inefficiency and limited fault tolerance in single-agent approaches for complex, lengthy tasks in Minecraft by proposing CausalMACE, a causality planning framework for multi-agent systems, which achieves state-of-the-art performance in cooperative tasks.
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.