Game Generation via Large Language Models

Chengpeng HU; Yunlong ZHAO; Jialin LIU

doi:10.1109/CoG60054.2024.10645597

Game Generation via Large Language Models

Chengpeng HU, Yunlong ZHAO, Jialin LIU^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

Abstract

Recently, the emergence of large language models (LLMs) has unlocked new opportunities for procedural content generation. However, recent attempts mainly focus on level generation for specific games with defined game rules such as Super Mario Bros. and Zelda. This paper investigates the game generation via LLMs. Based on video game description language, this paper proposes an LLM-based framework to generate game rules and levels simultaneously. Experiments demonstrate how the framework works with prompts considering different combinations of context. Our findings extend the current applications of LLMs and offer new insights for generating new games in the area of procedural content generation.

Original language	English
Title of host publication	Proceedings of the 2024 IEEE Conference on Games, CoG 2024
Publisher	IEEE Computer Society
Number of pages	4
ISBN (Electronic)	9798350350678
DOIs	https://doi.org/10.1109/CoG60054.2024.10645597
Publication status	Published - Aug 2024
Externally published	Yes
Event	6th Annual IEEE Conference on Games, CoG 2024 - Milan, Italy Duration: 5 Aug 2024 → 8 Aug 2024

Publication series

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
ISSN (Print)	2325-4270
ISSN (Electronic)	2325-4289

Conference

Conference	6th Annual IEEE Conference on Games, CoG 2024
Country/Territory	Italy
City	Milan
Period	5/08/24 → 8/08/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Funding

This work was supported by the National Key R&D Program of China (Grant No. 2023YFE0106300), the National Natural Science Foundation of China (Grant No. 62250710682), the Guangdong Major Project of Basic and Applied Basic Research (Grant No. 2023B0303000010), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), and the Research Institute of Trustworthy Autonomous Systems.

Keywords

game design
general video game playing
large language model
Procedural content generation
video game description language

Access to Document

10.1109/CoG60054.2024.10645597

Cite this

@inproceedings{692ec1e460374b88a18a38bbc17ede87,

title = "Game Generation via Large Language Models",

abstract = "Recently, the emergence of large language models (LLMs) has unlocked new opportunities for procedural content generation. However, recent attempts mainly focus on level generation for specific games with defined game rules such as Super Mario Bros. and Zelda. This paper investigates the game generation via LLMs. Based on video game description language, this paper proposes an LLM-based framework to generate game rules and levels simultaneously. Experiments demonstrate how the framework works with prompts considering different combinations of context. Our findings extend the current applications of LLMs and offer new insights for generating new games in the area of procedural content generation.",

keywords = "game design, general video game playing, large language model, Procedural content generation, video game description language",

author = "Chengpeng HU and Yunlong ZHAO and Jialin LIU",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 6th Annual IEEE Conference on Games, CoG 2024 ; Conference date: 05-08-2024 Through 08-08-2024",

year = "2024",

month = aug,

doi = "10.1109/CoG60054.2024.10645597",

language = "English",

series = "IEEE Conference on Computatonal Intelligence and Games, CIG",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of the 2024 IEEE Conference on Games, CoG 2024",

address = "United States",

}

Game Generation via Large Language Models. / HU, Chengpeng; ZHAO, Yunlong; LIU, Jialin.
Proceedings of the 2024 IEEE Conference on Games, CoG 2024. IEEE Computer Society, 2024. (IEEE Conference on Computatonal Intelligence and Games, CIG).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - Game Generation via Large Language Models

AU - HU, Chengpeng

AU - ZHAO, Yunlong

AU - LIU, Jialin

PY - 2024/8

Y1 - 2024/8

N2 - Recently, the emergence of large language models (LLMs) has unlocked new opportunities for procedural content generation. However, recent attempts mainly focus on level generation for specific games with defined game rules such as Super Mario Bros. and Zelda. This paper investigates the game generation via LLMs. Based on video game description language, this paper proposes an LLM-based framework to generate game rules and levels simultaneously. Experiments demonstrate how the framework works with prompts considering different combinations of context. Our findings extend the current applications of LLMs and offer new insights for generating new games in the area of procedural content generation.

AB - Recently, the emergence of large language models (LLMs) has unlocked new opportunities for procedural content generation. However, recent attempts mainly focus on level generation for specific games with defined game rules such as Super Mario Bros. and Zelda. This paper investigates the game generation via LLMs. Based on video game description language, this paper proposes an LLM-based framework to generate game rules and levels simultaneously. Experiments demonstrate how the framework works with prompts considering different combinations of context. Our findings extend the current applications of LLMs and offer new insights for generating new games in the area of procedural content generation.

KW - game design

KW - general video game playing

KW - large language model

KW - Procedural content generation

KW - video game description language

UR - http://www.scopus.com/inward/record.url?scp=85203551948&partnerID=8YFLogxK

U2 - 10.1109/CoG60054.2024.10645597

DO - 10.1109/CoG60054.2024.10645597

M3 - Conference paper (refereed)

AN - SCOPUS:85203551948

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

BT - Proceedings of the 2024 IEEE Conference on Games, CoG 2024

PB - IEEE Computer Society

T2 - 6th Annual IEEE Conference on Games, CoG 2024

Y2 - 5 August 2024 through 8 August 2024

ER -

Game Generation via Large Language Models

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this