arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.23875cs.MA
收藏

自适应演化多智能体框架用于实时战略场景中的高效决策

Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

School of Cyber Science and Technology, Beihang University(北京航空航天大学网络空间安全学院);Naval Aviation University(海军航空大学);Military Science Academy(军事科学院);National University of Defense Technology(国防科技大学);China Academy of Electronics and Information Technology(中国电子科技集团公司第十四研究所);School of Automation Science and Electrical Engineering, Beihang University(北京航空航天大学自动化科学与电气工程学院)

Li Ma, Hao Peng, Yiming Wang, Jie Liu, Kongjing Gu, Kangli Zi, Na Han, Hui Lin

AI总结:

本文提出SEMA框架,通过自适应校准模型偏差和动态观察剪枝,提升实时战略场景中的决策效率与一致性,实验显示其在StarCraft II地图上胜率更高且决策延迟降低超过50%。

摘要:

大型语言模型(LLMs)在复杂推理中展现出卓越潜力,开创了动态环境中自主智能体决策的新范式。然而,在实时战略(RTS)场景中,LLMs面临关键的速度-质量权衡问题。具体而言,广阔的状态空间和时间限制使推理延迟成为阻碍,而随机规划错误会破坏逻辑一致性。为解决这些问题,我们提出了SEMA(自适应演化多智能体)框架,旨在高绩效、低延迟的RTS环境中进行决策。该协作多智能体框架通过在回合内评估和跨回合分析来实现自我进化。我们进一步基于结构熵引入动态观察剪枝,以拓扑方式建模游戏状态。通过将高维数据压缩为核心语义信息,该方法显著减少了推理时间。我们还开发了一种混合知识-记忆机制,整合微轨迹、宏经验和分层领域知识,从而增强战略适应性和决策一致性。在多个StarCraft II地图上的实验表明,SEMA在胜率方面优于其他方法,同时将平均决策延迟降低了超过50%,验证了其在复杂RTS场景中的效率和鲁棒性。

英文摘要:

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑