GPT for Games: An Updated Scoping Review (2020-2024)

2024-11-01

arXiv.org

AI Summary

Despite rapid adoption of GPT models in game development, the field lacks a systematic synthesis of applications, emerging trends, and critical research gaps. Method: We conduct a rigorous bibliometric review of 177 peer-reviewed publications (including 122 from 2024) spanning 2020–2024, employing standardized literature coding, thematic clustering, and cross-year trend analysis. Contribution/Results: We introduce the first five-dimensional taxonomy for GPT applications in games—covering procedural content generation, human-AI co-design, game-playing agents, AI-driven testing, and user research—alongside the most comprehensive GPT-in-gaming application map to date. Our analysis identifies two pivotal research gaps: (1) technical limitations at the boundaries of current GPT capabilities, and (2) insufficient understanding of dynamic human-AI interaction mechanisms. We further propose an extensible domain-knowledge modeling methodology. These findings provide empirically grounded guidance for AI-augmented game development, paradigm shifts in design practice, and experience optimization.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Game Theory and Economic Paradigms: Cooperative Game Theory
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Due to GPT's impressive generative capabilities, its applications in games are expanding rapidly. To offer researchers a comprehensive understanding of the current applications and identify both emerging trends and unexplored areas, this paper introduces an updated scoping review of 177 articles, 122 of which were published in 2024, to explore GPT's potential for games. By coding and synthesizing the papers, we identify five prominent applications of GPT in current game research: procedural content generation, mixed-initiative game design, mixed-initiative gameplay, playing games, and game user research. Drawing on insights from these application areas and emerging research, we propose future studies should focus on expanding the technical boundaries of the GPT models and exploring the complex interaction dynamics between them and users. This review aims to illustrate the state of the art in innovative GPT applications in games, offering a foundation to enrich game development and enhance player experiences through cutting-edge AI innovations.

Problem

• Explore GPT's applications in games from 2020-2024
• Identify trends and gaps in GPT's use for game research
• Propose future studies on GPT's technical and user interaction advancements

Innovation

• Scoping review of 177 GPT game articles
• Identifies five key GPT game applications
• Proposes future GPT technical boundary expansion