Grammar and Gameplay-aligned RL for Game Description Generation with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tanaka, Tsunehiko, Simo-Serra, Edgar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913914616283136
author Tanaka, Tsunehiko
Simo-Serra, Edgar
author_facet Tanaka, Tsunehiko
Simo-Serra, Edgar
contents Game Description Generation (GDG) is the task of generating a game description written in a Game Description Language (GDL) from natural language text. Previous studies have explored generation methods leveraging the contextual understanding capabilities of Large Language Models (LLMs); however, accurately reproducing the game features of the game descriptions remains a challenge. In this paper, we propose reinforcement learning-based fine-tuning of LLMs for GDG (RLGDG). Our training method simultaneously improves grammatical correctness and fidelity to game concepts by introducing both grammar rewards and concept rewards. Furthermore, we adopt a two-stage training strategy where Reinforcement Learning (RL) is applied following Supervised Fine-Tuning (SFT). Experimental results demonstrate that our proposed method significantly outperforms baseline methods using SFT alone. Our code is available at https://github.com/tsunehiko/rlgdg
format Preprint
id arxiv_https___arxiv_org_abs_2503_15783
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grammar and Gameplay-aligned RL for Game Description Generation with LLMs
Tanaka, Tsunehiko
Simo-Serra, Edgar
Computation and Language
Artificial Intelligence
Game Description Generation (GDG) is the task of generating a game description written in a Game Description Language (GDL) from natural language text. Previous studies have explored generation methods leveraging the contextual understanding capabilities of Large Language Models (LLMs); however, accurately reproducing the game features of the game descriptions remains a challenge. In this paper, we propose reinforcement learning-based fine-tuning of LLMs for GDG (RLGDG). Our training method simultaneously improves grammatical correctness and fidelity to game concepts by introducing both grammar rewards and concept rewards. Furthermore, we adopt a two-stage training strategy where Reinforcement Learning (RL) is applied following Supervised Fine-Tuning (SFT). Experimental results demonstrate that our proposed method significantly outperforms baseline methods using SFT alone. Our code is available at https://github.com/tsunehiko/rlgdg
title Grammar and Gameplay-aligned RL for Game Description Generation with LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.15783