{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:50:18Z","timestamp":1777902618960,"version":"3.51.4"},"reference-count":34,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T00:00:00Z","timestamp":1769299200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100031839","name":"korea research institute for defense technology planning and advancement","doi-asserted-by":"publisher","award":["16-202-210-025"],"award-info":[{"award-number":["16-202-210-025"]}],"id":[{"id":"10.13039\/100031839","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["SIMULATION"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:p>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\u2013condition\u2013action (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.<\/jats:p>","DOI":"10.1177\/00375497251415245","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T06:46:59Z","timestamp":1769410019000},"page":"255-276","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-based wargame scenario generation with domain ontology and ECA rules"],"prefix":"10.1177","volume":"102","author":[{"given":"Yongsu","family":"Bae","sequence":"first","affiliation":[{"name":"Republic of Korea Navy, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seokju","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1581-917X","authenticated-orcid":false,"given":"Kyong-Ho","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyunghwa","family":"Lee","sequence":"additional","affiliation":[{"name":"ITCEN ENTEC, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Louie R Nandi A Fang W 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.","DOI":"10.48550\/arXiv.2407.00870"},{"key":"e_1_3_3_3_2","first-page":"86","article-title":"Scenecraft: automating interactive narrative scene generation in digital games with large language models","volume":"19","author":"Kumaran V","year":"2023","unstructured":"Kumaran V, Rowe J, Mott B, et al. Scenecraft: automating interactive narrative scene generation in digital games with large language models. Proc AAAI Conf Artif Intell Interact Digit Entertain 2023; 19: 86\u201396.","journal-title":"Proc AAAI Conf Artif Intell Interact Digit Entertain"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1177\/00375497241296542"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642159"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/e22080861"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10669-012-9426-1"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1177\/0037549707085541"},{"key":"e_1_3_3_9_2","volume-title":"Wargaming handbook","author":"UK and Ministry of Defence","year":"2017","unstructured":"UK and Ministry of Defence. Wargaming handbook. London: Ministry of Defence, 2017."},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITOEC57671.2023.10291525"},{"key":"e_1_3_3_11_2","article-title":"The methodological machinery of wargaming: a path toward discovering wargaming\u2019s epistemological foundations","volume":"26","author":"Banks DE.","year":"2024","unstructured":"Banks DE. The methodological machinery of wargaming: a path toward discovering wargaming\u2019s epistemological foundations. Int Stud Rev 2024; 26: viae002.","journal-title":"Int Stud Rev"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1177\/15485129211073126"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/66926.66946"},{"key":"e_1_3_3_14_2","first-page":"36","volume-title":"Advances in neural information processing systems","author":"Rafailov R","year":"2023","unstructured":"Rafailov R, Sharma A, Mitchell E, 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."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.21140\/mcuj.20211202003"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2560494"},{"key":"e_1_3_3_17_2","volume-title":"Empowering military decision support through the synergy of AI and simulation","author":"van Oijen J","year":"2023","unstructured":"van Oijen J, de Marez Oyens P. Empowering military decision support through the synergy of AI and simulation. La Spezia: STO, 2023."},{"key":"e_1_3_3_18_2","volume-title":"Human-AI cooperation to benefit military decision making","author":"Van Den Bosch K","year":"2018","unstructured":"Van Den Bosch K, Bronkhorst A. Human-AI cooperation to benefit military decision making. Brussels: NATO, 2018."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12052494"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7224-1_27"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00295"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.3012352"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2024.07.012"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCIS61231.2024.10540749"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3584931.3606960"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9097"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/505168.505170"},{"key":"e_1_3_3_28_2","volume-title":"Ontology: a practical guide","author":"Pease A.","year":"2011","unstructured":"Pease A. Ontology: a practical guide. Angwin, CA: Articulate Software Press, 2011."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Dubey A Jauhri A Pandey A et al. The llama 3 herd of models. arXiv. DOI: 10.48550\/arXiv.2407.21783.","DOI":"10.48550\/arXiv.2407.21783"},{"key":"e_1_3_3_30_2","unstructured":"Warfare Sims. Command: modern air\/naval operations (CMANO). https:\/\/www.cmo-db.com\/en\/"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Wiseman S Shieber SM Rush AM. Challenges in data-to-document generation. arXiv. DOI: 10.48550\/arXiv.1707.08052.","DOI":"10.48550\/arXiv.1707.08052"},{"key":"e_1_3_3_32_2","first-page":"93","volume-title":"European conference on computer vision","author":"Ding W","year":"2024","unstructured":"Ding W, Cao Y, Zhao D, et al. RealGen: retrieval augmented generation for controllable traffic scenarios. In: European conference on computer vision. New York: ACM, 2024, pp. 93\u2013110."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1462"},{"key":"e_1_3_3_34_2","first-page":"5794","volume-title":"Proceedings of the 29th international conference on computational linguistics","author":"Chhun C","year":"2022","unstructured":"Chhun C, Colombo P, Suchanek F, et al. Of human criteria and automatic metrics: a benchmark of the evaluation of story generation. In: Calzolari N, Huang C-R, Kim H, et al. (eds) Proceedings of the 29th international conference on computational linguistics. Gyeongju: International Committee on Computational Linguistics, 2022, pp. 5794\u20135836."},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.89"}],"container-title":["SIMULATION"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00375497251415245","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/00375497251415245","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00375497251415245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:35:03Z","timestamp":1777635303000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/00375497251415245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1177\/00375497251415245"],"URL":"https:\/\/doi.org\/10.1177\/00375497251415245","relation":{},"ISSN":["0037-5497","1741-3133"],"issn-type":[{"value":"0037-5497","type":"print"},{"value":"1741-3133","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,25]]}}}