AIApr 11, 2024

Game Generation via Large Language Models

arXiv:2404.08706v225 citationsh-index: 52024 IEEE Conference on Games (CoG)
Originality Synthesis-oriented
AI Analysis

This work extends LLM applications in procedural content generation, offering new insights for creating new games, though it appears incremental as it builds on existing methods for specific games.

The paper tackles the problem of generating complete games, including rules and levels, using large language models, proposing a framework based on video game description language and demonstrating its functionality with various prompts.

Recently, the emergence of large language models (LLMs) has unlocked new opportunities for procedural content generation. However, recent attempts mainly focus on level generation for specific games with defined game rules such as Super Mario Bros. and Zelda. This paper investigates the game generation via LLMs. Based on video game description language, this paper proposes an LLM-based framework to generate game rules and levels simultaneously. Experiments demonstrate how the framework works with prompts considering different combinations of context. Our findings extend the current applications of LLMs and offer new insights for generating new games in the area of procedural content generation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes