Abstract

Procedural Content Generation (PCG) has long enabled efficient and varied game level creation. However, integrating high-level design intentions and game mechanics into complex 3D environments remains challenging. This paper introduces a comprehensive framework that transforms narrative-level descriptions into playable 3D game levels. First, Large Language Models (LLMs) parse natural language descriptions into a structured Game Level Description Language (GLDL), capturing essential spatial constraints. Next, we model level generation as a Facility Layout Optimization problem, ensuring that facility placements and configurations adhere to specified design criteria. Through comprehensive experiments—including automated constraint evaluations and agent-based simulations—our approach ensures both the feasibility and stability of constraints extracted from text. We confirm that the resulting levels remain interactive, reasonable, and controllable to their original specifications.

Citation

Xu, K., & Verbrugge, C. (2025, April). Constraint Is All You Need: Optimization-Based 3D Level Generation with LLMs. In Proceedings of the 20th International Conference on the Foundations of Digital Games (FDG 2025) (pp. 1–13).

@inproceedings{xu2025constraintAllYouNeed,
  author    = {Kaijie Xu and Clark Verbrugge},
  title     = {Constraint Is All You Need: Optimization-Based 3D Level Generation with LLMs},
  booktitle = {Proceedings of the 20th International Conference on the Foundations of Digital Games},
  year      = {2025},
  month     = {Apr},
  pages     = {1--13}
}