mlsanityData to 14 Oct 2026

Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft

arXiv 2503.03505 ↗First posted 5 Mar 2025cs.AIcited by 5

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

Abstract (arXiv)

Recent advancements in Large Language Model~(LLM)-based Multi-Agent Systems (MAS) have demonstrated remarkable potential for tackling complex decision-making tasks. However, existing frameworks inevitably rely on serialized execution paradigms, where agents must complete sequential LLM planning before taking action. This fundamental constraint severely limits real-time responsiveness and adaptation, which is crucial in dynamic environments with ever-changing scenarios like Minecraft. In this paper, we propose a novel parallelized planning-acting framework for LLM-based MAS, featuring a dual-thread architecture with interruptible execution to enable concurrent planning and acting. Specifically, our framework comprises two core threads: (1) a planning thread driven by a centralized memory system, maintaining synchronization of environmental states and agent communication to support dynamic decision-making; and (2) an acting thread equipped with a comprehensive skill library, enabling automated task execution through recursive decomposition. Extensive experiments on Minecraft demonstrate the effectiveness of the proposed framework.

Key facts. Cited by 5 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 22 of its 41 references that are in the map. First posted on arXiv 5 Mar 2025.

Builds on

22 of 41 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks7 Aug
  2. 2024Odyssey: Empowering Minecraft Agents with Open-World Skills22 Jul
  3. 2023Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games1 Dec
  4. 2023See and Think: Embodied Agent in Virtual Environment26 Nov
  5. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory25 May
  6. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge17 Jun

Other references · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  6. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  7. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 106
  8. 2024MARG: Multi-Agent Review Generation for Scientific Paperscited by 104
  9. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 88
  10. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  11. 2023MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perceptioncited by 67
  12. 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Controlcited by 53
4 more
  1. 2023Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worldscited by 45
  2. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 36
  3. 2024VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraftcited by 35
  4. 2024LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligencecited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Dynamic Speculative Agent Planningcited by 12
  2. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  3. 2025Cochain: Balancing Insufficient and Excessive Collaboration in LLM Agent Workflowscited by 2
  4. 2026ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Managementcited by 2
  5. 2025Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  2. 2025OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
  3. 2026MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents
  4. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
  5. 2025BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks
  6. 2026SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction
  7. 2026Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft
  8. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks