Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models
CAAI Transactions on Intelligence Technology · 2026-06 · 11 (3) · 739-753
DOI: 10.1049/cit2.70108 ↗Kurz gefasst
Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 27.02.2026. Verfasst von Xiali Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Large language models (LLMs) have made remarkable advances in natural language processing, demonstrating great potential in modelling structured sequences. However, adapting these capabilities to machine gaming tasks such as Go remains challenging due to limitations in strategy generalisation and optimisation efficiency. This paper presents multitype game optimisation (MyGO), a two‐stage fine‐tuning framework tailored for two‐player perfect information board games, exploring the applicability of LLMs to nonlinguistic decision‐making domains. In the supervised fine‐tuning stage, we propose a unified structural encoding method, action semantic unit (ASU), which efficiently converts heterogeneous game records into discrete token sequences compatible with LLMs. In the reinforcement learning stage, we design TA‐PPO (token‐level adaptive proximal policy optimisation), an enhanced PPO‐based algorithm to address the issue of sparse feedback commonly encountered in game reinforcement learning. Experimental results demonstrate that the fine‐tuned models achieve superior or comparable performance to traditional game‐playing algorithms in terms of strategy quality, rule generalisation and inference efficiency. This work provides a scalable paradigm for fine‐tuning LLMs in complex decision‐making tasks and lays a foundation for future research in game AI and generalisable strategy optimisation.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, X., Gu, J., He, F., Xiao, Y., Jia, Y., & Lan, P. (2026). Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models. CAAI Transactions on Intelligence Technology, 11(3), 739-753. https://doi.org/10.1049/cit2.70108
Vancouver
Li X, Gu J, He F, Xiao Y, Jia Y, Lan P. Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models. CAAI Transactions on Intelligence Technology. 2026;11(3):739-753. doi:10.1049/cit2.70108
BibTeX
@article{Li2026,
author = {Li, Xiali and Gu, Jingshi and He, Feifan and Xiao, Yang and Jia, Yuanli and Lan, Ping},
title = {Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models},
journal = {CAAI Transactions on Intelligence Technology},
year = {2026},
volume = {11},
number = {3},
pages = {739--753},
doi = {10.1049/cit2.70108}
}
EUVIMED