兵棋推演是軍事規劃的重要工具,能模擬戰場環境並評估行動方案。然而,傳統方法耗時且難以應對瞬息萬變的現代戰場。隨著「大語言模型」(Large Language Model, LLM)技術的發展與進步,特別是GPT系列的發展,兵棋推演迎來革新之契機。[1]本文聚焦於LLM在國軍兵推的應用前景,探討其潛在優勢與風險。借鑒美軍相關研究,尤其是「作戰行動方案GPT」(Course-of-Action-GPT, COA-GPT)的實踐,本文分析未來如何將此技術融入我國軍事兵棋推演,提升決策效率,為國軍現代化提供新思維,促進軍事AI的本土化發展。[2]
註釋
[1] Tom Brown and Ben Mann et al., "Language Models Are Few-Shot Learners," Advances in Neural Information Processing Systems ,Vol.33 (2020), pp. 1877-1901.
[2] Vinicius G. Goecks and Nicholas Waytowich, "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) (IEEE, 2024), pp.1-10.