mlsanityData to 14 Oct 2026

CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

arXiv 2508.18797 ↗First posted 26 Aug 2025cs.AIcited by 8

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 41 references that are in the map. First posted on arXiv 26 Aug 2025.

Builds on

24 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks7 Aug
  2. 2024Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification24 May
  3. 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration14 Nov
  4. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models10 Nov

Other references · 20

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  3. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  4. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  5. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  6. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  7. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  8. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 166
  9. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 150
  10. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 97
  11. 2023Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debatecited by 94
  12. 2023Causal Discovery with Language Models as Imperfect Expertscited by 64
8 more
  1. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 61
  2. 2023Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Modelscited by 39
  3. 2024VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraftcited by 35
  4. 2024Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answeringcited by 18
  5. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15
  6. 2015Selective Greedy Equivalence Search: Finding Optimal Bayesian Networks Using a Polynomial Number of Score Evaluationscited by 14
  7. 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformercited by 14
  8. 2021Instrumental Variable-Driven Domain Generalization with Unobserved Confounderscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026MultiWorld: Scalable Multi-Agent Multi-View Video World Modelscited by 23
  2. 2025ContextNav: Towards Agentic Multimodal In-Context Learningcited by 10
  3. 2026Experience Transfer for Multimodal LLM Agents in Minecraft Gamecited by 5
  4. 2025The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Gamescited by 3
  5. 2026Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Gamecited by 3
  6. 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failurescited by 1
  7. 2026EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigationcited by 0
  8. 2026GenCoord: Executable Commitments for Embodied LLM Agents under Private Informationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft
  2. 2024TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
  3. 2026MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents
  4. 2025Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft
  5. 2025CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
  6. 2026WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
  7. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
  8. 2025BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks