EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BASL: Grounding LLM-Based Historical Battle Simulation Using Execution Difficulty and Tactical Necessity

Masao Kubo, Ryugo Okuyama, Hiroshi Sato, Akihiro Yamaguchi

Electronics · 17.11.2026 · 15 (22) · 5364

DOI: 10.3390/electronics15225364 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 17.11.2026. Verfasst von Masao Kubo und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Asian Office of Aerospace Research and Development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BattleAgent (BA) uses large language models (LLMs) to select tactical Actions flexibly, but LLM decisions can conflict with the simulation state, execution rules, or tactical situation. We divide this LLM–simulation grounding gap into two components, the Action-execution grounding gap and the tactical Action-selection grounding gap, and introduce simulation grounding fidelity (SGF) to assess them. We propose BASL (BattleAgent with a State Ledger), in which the simulator enforces Action feasibility, calculates execution Difficulty D(a,St) and tactical Necessity N(a,St) from the current state, and provides them to the LLM as advisory information while leaving the final Action choice to the LLM. Experiments used four battlefields: Crécy, Poitiers, Agincourt, and Falkirk. Presenting both D and N raised the tactical-grounding index SGFT from 65.105 to 67.682. Across four LLMs, presenting Difficulty reduced mean selected Difficulty, whereas presenting Necessity increased mean selected Necessity. In 50 Agincourt simulations, the simulator’s checks found no violations of movement distance, weapon range, or Action feasibility. Thus, presenting D and N together with instructions to prefer lower-risk and sufficiently necessary Actions shifts Action selection in their direction, while BASL executes Actions according to the simulator’s rules. We do not claim that the resulting decisions are tactically optimal or better than those of human commanders.

Förderung

  • Asian Office of Aerospace Research and Development

Zitieren

APA

Kubo, M., Okuyama, R., Sato, H., & Yamaguchi, A. (2026). BASL: Grounding LLM-Based Historical Battle Simulation Using Execution Difficulty and Tactical Necessity. Electronics, 15(22), 5364. https://doi.org/10.3390/electronics15225364

Vancouver

Kubo M, Okuyama R, Sato H, Yamaguchi A. BASL: Grounding LLM-Based Historical Battle Simulation Using Execution Difficulty and Tactical Necessity. Electronics. 2026;15(22):5364. doi:10.3390/electronics15225364

BibTeX
@article{Kubo2026,
  author = {Kubo, Masao and Okuyama, Ryugo and Sato, Hiroshi and Yamaguchi, Akihiro},
  title = {BASL: Grounding LLM-Based Historical Battle Simulation Using Execution Difficulty and Tactical Necessity},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5364},
  doi = {10.3390/electronics15225364}
}
Kostenlos starten →