自动化学报2025，Vol.51Issue(6)：1205-1217,13.DOI:10.16383/j.aas.c240657
基于大语言模型的兵棋推演智能决策技术
Decision Technology Based on Large Language Model for Wargame
摘要
Abstract
Wargame simulates real confrontations by controlling the behavior of agents,which has important re-search significance in the field of intelligent decision-making.Most existing research has focused on knowledge-driv-en rule-based agents or data-driven learning agents.Although these methods have made some progress in small-scale wargame,the high acquisition cost and weak generalization of knowledge rules,as well as the low stability of learning algorithms and the high computational requirements of the learning process,make it difficult to be flexibly applied in large-scale wargame that are closer to real scenarios.In order to alleviate the above problems,a large-scale multi-agent hierarchical task planning framework based on large language model is proposed,which uses large language model to perfom coarse-grained task planning at the team level and fine-grained task decomposition at the individual level,which focuses on strategy generation through planning,communication,memory,and reflection.Compared to previous works,the proposed method alleviates the problem of generalization effectively and can main-tain a certain degree of self-improvement ability while avoiding high cost training of agent parameters.Experiment shows that our model can defeat elite AI with a high winning rate.Furthermore,our model also has self-improve ability,generalization ability,and interpretability ability,which has significant advantages in large-scale adversarial environment.关键词
兵棋推演/策略生成/大语言模型/分层任务规划Key words
Wargame/policy generation/large language model/hierarchical task planning引用本文复制引用
王彤,赵美静,徐沛,尹奇跃,焦建彬,黄凯奇..基于大语言模型的兵棋推演智能决策技术[J].自动化学报,2025,51(6):1205-1217,13.基金项目
中国科学院战略性先导科技专项基金(XDA27010103),国家资助博士后研究人员计划(GZC20232995),中国博士后科学基金(2024M763533)资助Supported by Strategic Priority Research Program of Chinese Academy of Sciences(XDA27010103),Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(GZC20232995),and China Postdoctoral Science Foundation(2024M763533) （XDA27010103）
