Large Language Models and Games: A Survey and Roadmap

2024/02/28 by Roberto Gallotta, Graham Todd, Marvin Zammit +4 · 2 voices · 11 citations
Computer Science · #cs.CL #cs.AI #cs.HC

paper · pdf · doi:10.1109/tg.2024.3461510

arxiv published 2024/02/28 · arxiv updated 2024/12/09

Abstract

Recent years have seen an explosive increase in research on large language models (LLMs), and accompanying public engagement on the topic. While starting as a niche area within natural language processing, LLMs have shown remarkable potential across a broad range of applications and domains, including games. This paper surveys the current state of the art across the various applications of LLMs in and for games, and identifies the different roles LLMs can take within a game. Importantly, we discuss underexplored areas and promising directions for future uses of LLMs in games and we reconcile the potential and limitations of LLMs within the games domain. As the first comprehensive survey and roadmap at the intersection of LLMs and games, we are hopeful that this paper will serve as the basis for groundbreaking research and innovation in this exciting new field.

Cited by

• Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs
• Robust LLM Training Infrastructure at ByteDance
• Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs
• Can Large Language Models Master Complex Card Games?
• Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments
• Rule Synergy Analysis using LLMs: State of the Art and Implications
• Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
• GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games
• UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games
• Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models
• How LLMs are Shaping the Future of Virtual Reality

Discussions

• Large Language Models and Games: A Survey and Roadmap [hn, 3 points, 0 comments]
• I'm interested, and want to read it. Possibly interesting to you, we recently posted this survey of LLMs for games - a bit of a broader take, but NPCs are in there: arxiv.org/abs/2402.18659 [bsky, 1 points, 0 comments]

Related

• Large Language Models and Video Games: A Preliminary Scoping Review
• Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard
• A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges
• Game Generation via Large Language Models
• GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps