Large Language Models and Video Games: A Preliminary Scoping Review
Penny Sweetser
TL;DR
This work provides a first, structured view of how large language models are being applied to video games by conducting a scoping review of 76 papers published between 2022 and early 2024. It identifies four core themes—game AI and agents, game development and play, narrative/story/dialogue, and game research and reviews—along with an auxiliary set on data-set–driven recommendation research (LLM4Rec). The review documents a range of approaches, from GPT-based agents and RL integrations to NPC dialogue generation and PCG via prompts, highlighting GPT dominance and notable successes as well as limitations in reasoning, coherence, and unpredictability. The findings offer a foundation for future research and practical guidance for designers and researchers seeking to leverage LLMs in games, while underscoring the need for systematic evaluation as the field moves quickly.
Abstract
Large language models (LLMs) hold interesting potential for the design, development, and research of video games. Building on the decades of prior research on generative AI in games, many researchers have sped to investigate the power and potential of LLMs for games. Given the recent spike in LLM-related research in games, there is already a wealth of relevant research to survey. In order to capture a snapshot of the state of LLM research in games, and to help lay the foundation for future work, we carried out an initial scoping review of relevant papers published so far. In this paper, we review 76 papers published between 2022 to early 2024 on LLMs and video games, with key focus areas in game AI, game development, narrative, and game research and reviews. Our paper provides an early state of the field and lays the groundwork for future research and reviews on this topic.