Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration

TL;DR

This survey reviews procedural content generation in games, highlighting recent integration of large language models, comparing various algorithms, and discussing future research directions in the field.

Contribution

It provides a comprehensive comparison of PCG algorithms, emphasizing the impact of LLMs and offering insights into future research opportunities.

Findings

LLMs have significantly advanced PCG capabilities.

Different algorithms produce diverse types of game content.

The survey identifies gaps and suggests future research directions.

Abstract

Procedural Content Generation (PCG) is defined as the automatic creation of game content using algorithms. PCG has a long history in both the game industry and the academic world. It can increase player engagement and ease the work of game designers. While recent advances in deep learning approaches in PCG have enabled researchers and practitioners to create more sophisticated content, it is the arrival of Large Language Models (LLMs) that truly disrupted the trajectory of PCG advancement. This survey explores the differences between various algorithms used for PCG, including search-based methods, machine learning-based methods, other frequently used methods (e.g., noise functions), and the newcomer, LLMs. We also provide a detailed discussion on combined methods. Furthermore, we compare these methods based on the type of content they generate and the publication dates of their respective papers. Finally, we identify gaps in the existing academic work and suggest possible directions for future research.