From Natural Language to Extensive-Form Game Representations

TL;DR

This paper presents a novel two-stage framework that uses Large Language Models and specialized modules to convert natural language game descriptions into extensive-form game representations, enabling automated analysis like Nash equilibrium computation.

Contribution

The paper introduces a two-stage, modular framework that enhances in-context learning for translating natural language into extensive-form game trees, addressing imperfect information challenges.

Findings

Framework significantly outperforms baseline models in accuracy

Modules are critical for handling imperfect information

Enables automation of game-theoretic analysis from natural language

Abstract

We introduce a framework for translating game descriptions in natural language into extensive-form representations in game theory, leveraging Large Language Models (LLMs) and in-context learning. Given the varying levels of strategic complexity in games, such as perfect versus imperfect information, directly applying in-context learning would be insufficient. To address this, we introduce 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 along 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 models in generating accurate extensive-form games, with each module playing a critical role in its success.