让大模型在即时战略游戏中更稳、更准地决策。
Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games
- 用自然语言构建状态机，引导大模型按规则行动
- 60%胜率击败最强内置AI，远超基线（0%）
- 适合研究大模型游戏智能与可解释决策的学者
本文提出记忆增强型状态机提示（MASMP），一种面向即时战略游戏的新型大模型智能体框架。针对现有方法存在的幻觉和决策碎片化问题，MASMP将状态机提示与记忆机制结合，实现结构化动作与长期战术一致性的统一。框架包含：(1) 基于自然语言的状态机架构，通过提示使大模型模拟有限状态机与行为树；(2) 轻量级记忆模块，可在决策周期间保留策略变量（如战术、优先单位）。在《星际争霸II》中的实验表明，MASMP对最高等级内置AI（Lv7）的胜率为60%，显著优于基线（0%）。案例研究显示，该方法在保持大模型语义理解能力的同时，通过严格的映射解决“知行差距”，实现可解释性与类状态机可靠性。本工作为复杂决策中神经与符号人工智能的融合提供了新范式。
原文摘要 · Abstract (English)
This paper proposes Memory-Augmented State Machine Prompting (MASMP), a novel framework for LLM agents in real-time strategy games. Addressing key challenges like hallucinations and fragmented decision-making in existing approaches, MASMP integrates state machine prompting with memory mechanisms to unify structured actions with long-term tactical coherence. The framework features: (1) a natural language-driven state machine architecture that guides LLMs to emulate finite state machines and behavior trees through prompts, and (2) a lightweight memory module preserving strategic variables (e.g., tactics, priority units) across decision cycles. Experiments in StarCraft II demonstrate MASMP's 60% win rate against the hardest built-in AI (Lv7), vastly outperforming baselines (0%). Case studies reveal the method retains LLMs' semantic comprehension while resolving the "Knowing-Doing Gap" through strict state-action mapping, achieving both interpretability and FSM-like reliability. This work establishes a new paradigm for combining neural and symbolic AI in complex decision-making.
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。