# From Natural Language to Extensive-Form Game Representations

arXiv: https://arxiv.org/abs/2501.17282 · HTML: https://mlsanity.com/paper/2501.17282/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis](https://mlsanity.com/paper/2312.05488/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering](https://mlsanity.com/paper/2308.12060/) (2023)
- [Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game](https://mlsanity.com/paper/2312.17515/) (2023)
- [Steering Language Models with Game-Theoretic Solvers](https://mlsanity.com/paper/2402.01704/) (2024)
- [Large Language Models Playing Mixed Strategy Nash Equilibrium Games](https://mlsanity.com/paper/2406.10574/) (2024)
- [Charting the Shapes of Stories with Game Theory](https://mlsanity.com/paper/2412.05747/) (2024)

## Built on by (most cited first, 6 of 6)

- [Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers](https://mlsanity.com/paper/2502.09053/) (2025)
- [LLM-Powered Preference Elicitation in Combinatorial Assignment](https://mlsanity.com/paper/2502.10308/) (2025)
- [GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory](https://mlsanity.com/paper/2602.12316/) (2026)
- [Distilling Game Code World Model Generation into Lightweight Large Language Models](https://mlsanity.com/paper/2605.24375/) (2026)
- [Discovering Expert-Level Nash Equilibrium Algorithms with Large Language Models](https://mlsanity.com/paper/2508.11874/) (2025)
- [Abstraction Agent](https://mlsanity.com/paper/2609.04303/) (2026)

## Abstract (arXiv)

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.