“What's the Game, then? Opportunities and Challenges for Runtime Behavior Generation”. Jennings, N., Wang, H., Li, I., Smith, J., Hartmann, B. ACM User Interface Software and Technology (UIST) 2024. 🎖️ Best Paper Award.

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 difcult to integrate with typical game development workfows. 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 fnd that our implementation is able to produce behaviors that result in signifcant downstream impacts to gameplay. We then conduct an interview study with n=13 game developers using GROMIT as a probe to elicit their current opinion on runtime behavior generation tools, and enumerate the specifc themes curtailing the wider use of such tools. We fnd that the main themes of concern are quality considerations, community expectations, and ft with developer workfows, and that several of the subthemes are unique to runtime behavior generation specifcally. We outline a future work agenda to address these concerns, including the need for additional guardrail systems for behavior generation.