CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

2025/08/26 by Chai, Qi, Zheng, Zhang, Ren, Junlong +3 · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2508.18797

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.

Citations

• VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft
• Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
• Large Language Models for Constrained-Based Causal Discovery
• VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft
• Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification
• Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering
• Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
• Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
• MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
• JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
• Causal Discovery with Language Models as Imperfect Experts
• Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
• Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations
• Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate
• Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
• Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
• Inner Monologue: Embodied Reasoning through Planning with Language Models
• Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
• Instrumental Variable-Driven Domain Generalization with Unobserved Confounders
• Selective Greedy Equivalence Search: Finding Optimal Bayesian Networks Using a Polynomial Number of Score Evaluations
• Causal Inference in the Presence of Latent Variables and Selection Bias

Cited by

• Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
• Leading the Follower: Learning Persuasive Agents in Social Deduction Games
• ContextNav: Towards Agentic Multimodal In-Context Learning

Related

• VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft
• CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
• Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
• TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
• MindAgent: Emergent Gaming Interaction