Construction Approach of LLM-empowered Tactical Wargame Decision-making Agents

Authors

• Dayong Liu, Army Arms University of PLA, Beijing 100072, China; PLA 32302 Troops
• Zhiming Dong, Army Arms University of PLA, Beijing 100072, China
• Qisheng Guo, Army Arms University of PLA, Beijing 100072, China
• Ang Gao, Academy of Army, Beijing 100072, China
• Xuehuan Qiu, Army Arms University of PLA, Beijing 100072, China

Abstract

Abstract: Decision-making agents are critical enablers for implementing human-machine, machinemachine, and hybrid human-machine adversarial interaction in tactical wargaming, where the intelligence level of the agent is crucial. To address the limitations of traditional decision agents such as insufficient adaptability, simplistic strategies, and high construction costs, a fusion decision framework driven by the large and small models was proposed. It specifically investigated the fusion approach of large language models with conventional decision-making agent construction approaches, including behavior trees, finite state machines, heuristic search, and deep reinforcement learning. New ideas and technical pathways are provided for the construction of tactical wargame decision-making agents.

Recommended Citation

Liu, Dayong; Dong, Zhiming; Guo, Qisheng; Gao, Ang; and Qiu, Xuehuan (2026) "Construction Approach of LLM-empowered Tactical Wargame Decision-making Agents," Journal of System Simulation: Vol. 38: Iss. 3, Article 16.
DOI: 10.16182/j.issn1004731x.joss.25-0298
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss3/16

First Page

758

Last Page

775

CLC

E917; TP391

Recommended Citation

Liu Dayong, Dong Zhiming, Guo Qisheng, et al. Construction Approach of LLM-empowered Tactical Wargame Decision-making Agents[J]. Journal of System Simulation, 2026, 38(3): 758-775.

Corresponding Author

Dong Zhiming

DOI

10.16182/j.issn1004731x.joss.25-0298