From Natural Language to Extensive-Form Game Representations

Deng, Shilong, Wang, Yongzhao and Savani, Rahul ORCID: 0000-0003-1262-7831 (2025) From Natural Language to Extensive-Form Game Representations .

Text p593.pdf - Open Access published version Download (1MB) | Preview

Abstract

We introduce a framework for translating game descriptions in natural language into game-theoretic extensive-form representations, leveraging Large Language Models (LLMs) and in-context learning. We find that a naive application of in-context learning struggles on this problem, in particular with imperfect information. To address this, we introduce GameInterpreter, a two-stage framework with specialized modules to enhance in-context learning, enabling it to divide and conquer the problem effectively. In the first stage, we tackle the challenge of imperfect information by developing a module that identifies information sets and the corresponding partial tree structure. With this information, the second stage leverages in-context learning alongside a self-debugging module to produce a complete extensive-form game tree represented using pygambit, the Python API of a recognized game-theoretic analysis tool called Gambit. Using this python representation enables the automation of tasks such as computing Nash equilibria directly from natural language descriptions. We evaluate the performance of the full framework, as well as its individual components, using various LLMs on games with different levels of strategic complexity. Our experimental results show that the framework significantly outperforms baseline approaches in generating accurate extensive-form games, with each module playing a critical role in its success.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	Code Generation, Extensive-Form Games, Gambit, Game Translation, Large Language Models
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	01 Aug 2025 10:56
Last Modified:	23 May 2026 10:25
Related Websites:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3193805
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.