Nicholas Jennings

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2024-153

August 2, 2024

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-153.pdf

Procedural content generation (PCG), the process of algorithmically creating game components instead of manually, has been a common tool of game development for decades. Recent advances in large language models (LLMs) enable the generation of game behaviors based on player input at runtime. Such code generation brings with it the possibility of entirely new gameplay interactions that may be difficult to integrate with typical game development workflows. We explore these implications through GROMIT, a novel LLM-based runtime behavior generation system for Unity. When triggered by a player action, GROMIT generates a relevant behavior which is compiled without developer intervention and incorporated into the game. We create three demonstration scenarios with GROMIT to investigate how such a technology might be used in game development. In a system evaluation we find that our implementation is able to produce behaviors that result in significant downstream impacts to gameplay. We outline a future work agenda to address these concerns, including the need for additional guardrail systems for behavior generation.

Advisors: Björn Hartmann

---

BibTeX citation:

@mastersthesis{Jennings:EECS-2024-153,
    Author= {Jennings, Nicholas},
    Editor= {Hartmann, Björn},
    Title= {Towards Runtime Behavior Generation in Games},
    School= {EECS Department, University of California, Berkeley},
    Year= {2024},
    Month= {Aug},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-153.html},
    Number= {UCB/EECS-2024-153},
    Abstract= {Procedural content generation (PCG), the process of algorithmically creating game components instead of manually, has been a common tool of game development for decades. Recent advances in large language models (LLMs) enable the generation of game behaviors based on player input at runtime. Such code generation brings with it the possibility of entirely new gameplay interactions that may be difficult to integrate with typical game development workflows. We explore these implications through GROMIT, a novel LLM-based runtime behavior generation system for Unity. When triggered by a player action, GROMIT generates a relevant behavior which is compiled without developer intervention and incorporated into the game. We create three demonstration scenarios with GROMIT to investigate how such a technology might be used in game development. In a system evaluation we find that our implementation is able to produce behaviors that result in significant downstream impacts to gameplay. We outline a future work agenda to address these concerns, including the need for additional guardrail systems for behavior generation.},
}

EndNote citation:

%0 Thesis
%A Jennings, Nicholas 
%E Hartmann, Björn 
%T Towards Runtime Behavior Generation in Games
%I EECS Department, University of California, Berkeley
%D 2024
%8 August 2
%@ UCB/EECS-2024-153
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-153.html
%F Jennings:EECS-2024-153