让AI在Minecraft中边规划边执行，大幅提升响应速度
Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft
- 双线程并行架构，计划与执行同时进行
- 实测在Minecraft中任务完成速度显著提升
- 适合需要实时反应的多智能体系统研究者
基于大语言模型的多智能体系统在处理复杂决策任务方面展现出巨大潜力。然而，现有框架普遍采用串行执行模式，即智能体必须完成全部语言模型规划后才能行动。这种根本性限制严重制约了实时响应与动态适应能力，尤其在像Minecraft这样场景不断变化的动态环境中。本文提出一种新型并行化规划-执行框架，采用双线程架构并支持可中断执行，实现规划与执行的并发。具体包括：(1) 由集中式记忆系统驱动的规划线程，维持环境状态同步与智能体通信，支持动态决策；(2) 配备完整技能库的执行线程，通过递归分解实现自动化任务执行。在Minecraft上的大量实验验证了该框架的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。