Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers

TL;DR

This comprehensive survey explores the bidirectional relationship between game theory and large language models, proposing a new taxonomy and outlining future research directions to advance understanding and application in this interdisciplinary area.

Contribution

It is the first systematic survey that categorizes research at the intersection of game theory and LLMs, introducing a novel taxonomy and identifying key challenges and future directions.

Findings

Four research perspectives identified: evaluation, improvement, societal impact, and model advancement.

Highlights mutual influence and potential for progress in both game theory and LLM fields.

Outlines key challenges and future research directions in this interdisciplinary area.

Abstract

Game theory is a foundational framework for analyzing strategic interactions, and its intersection with large language models (LLMs) is a rapidly growing field. However, existing surveys mainly focus narrowly on using game theory to evaluate LLM behavior. This paper provides the first comprehensive survey of the bidirectional relationship between Game Theory and LLMs. We propose a novel taxonomy that categorizes the research in this intersection into four distinct perspectives: (1) evaluating LLMs in game-based scenarios; (2) improving LLMs using game-theoretic concepts for better interpretability and alignment; (3) modeling the competitive landscape of LLM development and its societal impact; and (4) leveraging LLMs to advance game models and to solve corresponding game theory problems. Furthermore, we identify key challenges and outline future research directions. By systematically investigating this interdisciplinary landscape, our survey highlights the mutual influence of game theory and LLMs, fostering progress at the intersection of these fields.