Transferring Strategic Thinking From Large to Small Language Models for Multi-Agent Systems
ASME Open Journal of Engineering · 01.01.2026 · 5
DOI: 10.1115/1.4072118 ↗Kurz gefasst
Fachartikel in der Zeitschrift ASME Open Journal of Engineering, online erschienen am 08.07.2026. Verfasst von Nunzio Lore und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
As larger large language models (LLMs) demonstrate increasing proficiency in strategic reasoning tasks, their computational demands limit widespread deployment and the creation of agentic swarms. This study explores whether fine-tuning can yield smaller, more efficient models that achieve high performance in game-theoretic decision-making. We queried a large pretrained model on 20 diverse scenarios that associate canonical social dilemmas from game theory with social contexts, recording both the answers and the model’s reasoning. Responses obtained this way were then used to fine-tune a smaller model from the same family. Our results indicate that fine-tuning significantly improved the smaller model’s alignment with the larger model, achieving a mean overall increase of 46% (median: 32%) in behavioral similarity. Notably, improvements extended beyond training examples, with an 18% mean performance gain (median: 14%) in novel social contexts. When presented with re-parametrized versions of games from its training set, the fine-tuned model consistently reproduced its original strategies, indicating strong generalization to games with identical structures but altered payoffs. These findings suggest that fine-tuning enables smaller models to internalize aspects of strategic reasoning, enhancing their capacity for multi-agent interfacing while maintaining efficiency. This approach offers a promising pathway for developing cost-effective, specialized models for strategic decision-making, advancing both AI scalability and the study of computational social cognition.
Zitieren
APA
Lore, N., Ilami, S., & Heydari, B. (2026). Transferring Strategic Thinking From Large to Small Language Models for Multi-Agent Systems. ASME Open Journal of Engineering, 5. https://doi.org/10.1115/1.4072118
Vancouver
Lore N, Ilami S, Heydari B. Transferring Strategic Thinking From Large to Small Language Models for Multi-Agent Systems. ASME Open Journal of Engineering. 2026;5. doi:10.1115/1.4072118
BibTeX
@article{Lore2026,
author = {Lore, Nunzio and Ilami, Sepehr and Heydari, Babak},
title = {Transferring Strategic Thinking From Large to Small Language Models for Multi-Agent Systems},
journal = {ASME Open Journal of Engineering},
year = {2026},
volume = {5},
doi = {10.1115/1.4072118}
}
EUVIMED