Rapid advancements in the text generation capabilities of large language models (LLMs) have expanded their applicability across various domains, notably in scenario generation. This paper introduces a dynamic framework that utilizes the advanced text generation of LLMs to enhance scenario generation and decision-making in the wargame scenario. Our framework, fine-tuned on domain-specific data, automates the generation of complex and adaptive scenarios, responding to user interactions. It integrates a wargame domain ontology to ensure scenario accuracy and employs event–condition–action (ECA) rules for decision-making to improve the realism and explainability of scenarios. In addition, through direct preference optimization (DPO), the framework continually refines scenarios based on user feedback, thereby ensuring highly sophisticated simulations. This approach not only diminishes the time and resources needed for wargame scenario generation but also significantly boosts the effectiveness of training. Our findings highlight the transformative potential of LLMs in automating scenario generation and decision support for wargame simulations, thereby broadening the applicability of scenario generation research to various fields.
LouieRNandiAFangW, et al. Roleplay-doh: enabling domain-experts to create llm-simulated patients via eliciting and adhering to principles. arXiv. DOI: 10.48550/arXiv.2407.00870.
2.
KumaranVRoweJMottB, et al. Scenecraft: automating interactive narrative scene generation in digital games with large language models. Proc AAAI Conf Artif Intell Interact Digit Entertain2023; 19: 86–96.
3.
TeránOLegerPLópezM.Factors that drive market share and the oligopolistic character of cross-border B2C e-commerce: an agent-based scenario-analysis approach. SIMULATION2024; 101: 429–452.
4.
ShaikhOChaiVEGelfandM, et al. Rehearsal: simulating conflict to teach conflict resolution. In: Proceedings of the CHI conference on human factors in computing systems, Honolulu, HI, 11–16 May 2024, pp. 1–20. New York: Association for Computing Machinery.
5.
HodickỳJProcházkaDBaxaF, et al. Computer assisted wargame for military capability-based planning. Entropy2020; 22: 861.
6.
McCreightR.Scenario development: using geopolitical wargames and strategic simulations. Environ Syst Decis2013; 33: 21–32.
7.
ZhouSCaiWTurnerSJ, et al. Flexible state update mechanism for large-scale distributed wargame simulations. Simulation2007; 83: 707–719.
8.
UK and Ministry of Defence. Wargaming handbook. London: Ministry of Defence, 2017.
9.
ZhangJZhangYChuM, et al. A LLM-based simulation scenario aided generation method. In: 2023 IEEE 7th information technology and mechatronics engineering conference (ITOEC). Chongqing, 15–17 September 2023, pp. 1350–1354. New York: IEEE.
10.
BanksDE.The methodological machinery of wargaming: a path toward discovering wargaming’s epistemological foundations. Int Stud Rev2024; 26: viae002.
11.
DavisPKBrackenP.Artificial intelligence for wargaming and modeling. J Def Model Simul2022; 22: 25–40.
12.
McCarthyDDayalU.The architecture of an active database management system. ACM Sigmod Rec1989; 18: 215–224.
13.
RafailovRSharmaAMitchellE, et al. (eds) Direct preference optimization: your language model is secretly a reward model. In: Advances in neural information processing systems. Red Hook, NY: Curran Associates Inc, 2023, pp. 36.
14.
WaltersEM.Wargaming in professional military education: challenges and solutions. J Adv Mil Stud2021; 12: 81–114.
15.
SchwartzPJO’NeillDVBentzME, et al. (eds) AI-enabled wargaming in the military decision making process. In: Artificial intelligence and machine learning for multi-domain operations applications II. San Francisco, CA: SPIE, 2020, pp. 118–134.
16.
van OijenJde Marez OyensP. Empowering military decision support through the synergy of AI and simulation. La Spezia: STO, 2023.
17.
Van Den BoschKBronkhorstA. Human-AI cooperation to benefit military decision making. Brussels: NATO, 2018.
18.
ChuangH-MChengD-W.Conversational AI over military scenarios using intent detection and response generation. Appl Sci2022; 12: 2494.
19.
LiuYZhangJHuF, et al. A military domain knowledge-based question answering method based on large language model enhancement. In: WangHHanXLiuM, et al. (eds) China conference on knowledge graph and semantic computing. London: Springer, 2023, pp. 340–352.
20.
ChenYChuS.Large language models in wargaming: methodology application and robustness. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, 17–18 June 2024, pp. 2894–2903. New Work: IEEE.
21.
ConnollyBJ (ed.) Battlefield information and tactics engine (BITE): a multimodal large language model approach for battlespace management. In: Artificial intelligence and machine learning for multi-domain operations applications VI. San Francisco, CA: SPIE, 2024, p. 1305103.
22.
Zabala-LópezALinares-VásquezMHaiducS, et al. A survey of data-centric technologies supporting decision-making before deploying military assets. Def Technol2024; 42: 226–246.
23.
GoecksVGWaytowichN (eds). Coa-gpt: generative pre-trained transformers for accelerated course of action development in military operations. In: 2024 international conference on military communication and information systems (ICMCIS). New York: IEEE, 2024, pp. 01–10.
24.
JungHSeoWSongS, et al. Toward value scenario generation through large language models. In: Companion publication of the 2023 conference on computer supported cooperative work and social computing. New York: ACM, 2023, pp. 212–220.
25.
(FAIR)† MFARDT; BakhtinABrownNDinanE, et al. Human-level play in the game of diplomacy by combining language models with strategic reasoning. Science2022; 378: 1067–1074.
26.
NilesIPeaseA.Toward a standard upper ontology. In: WeltyCSmithB (eds) Proceedings of the 2nd international conference on formal ontology in information systems (FOIS-2001). New York: ACM, 2001, pp. 2–9.
27.
PeaseA.Ontology: a practical guide. Angwin, CA: Articulate Software Press, 2011.
28.
DubeyAJauhriAPandeyA, et al. The llama 3 herd of models. arXiv. DOI: 10.48550/arXiv.2407.21783.
WisemanSShieberSMRushAM.Challenges in data-to-document generation. arXiv. DOI: 10.48550/arXiv.1707.08052.
31.
DingWCaoYZhaoD, et al. RealGen: retrieval augmented generation for controllable traffic scenarios. In: European conference on computer vision. New York: ACM, 2024, pp. 93–110.
32.
XuJRenXZhangY, et al. A skeleton-based model for promoting coherence among sentences in narrative story generation. In: RiloffEChiangDHockenmaierJ, et al. (eds) Proceedings of the 2018 conference on empirical methods in natural language processing. New York: ACM, 2018, pp. 4306–4315.
33.
ChhunCColomboPSuchanekF, et al. Of human criteria and automatic metrics: a benchmark of the evaluation of story generation. In: CalzolariNHuangC-RKimH, et al. (eds) Proceedings of the 29th international conference on computational linguistics. Gyeongju: International Committee on Computational Linguistics, 2022, pp. 5794–5836.
34.
ParikhAWangXGehrmannS, et al. ToTTo: a controlled table-to-text generation dataset. In: WebberBCohnTHeY, et al. (eds) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). Stroudsburg, PA: Association for Computational Linguistics, 2020, pp. 1173–1186.
