Large Language Models in Game Development: Implications for Gameplay, Playability, and Player Experience

TL;DR

This study explores how integrating large language models into game development affects gameplay, personalization, and player experience, highlighting both benefits and challenges through a collaborative autoethnographic approach.

Contribution

It provides the first empirical insights into the impact of LLMs on game architecture, gameplay variability, and quality considerations in game engineering.

Findings

LLM integration increases variability and personalization in games.

Challenges include issues with correctness, difficulty calibration, and structural coherence.

The study offers preliminary empirical evidence on AI's influence on game design and engineering.

Abstract

This paper investigates how the integration of large language models influences gameplay, playability, and player experience in game development. We report a collaborative autoethnographic study of two game projects in which LLMs were embedded as architectural components. Reflective narratives and development artifacts were analyzed using gameplay, playability, and player experience as guiding constructs. The findings suggest that LLM integration increases variability and personalization while introducing challenges related to correctness, difficulty calibration, and structural coherence across these concepts. The study provides preliminary empirical insight into how generative AI integration reshapes established game constructs and introduces new architectural and quality considerations within game engineering practice.