mlsanityData to 7 Oct 2026

A Database-Driven Framework for 3D Level Generation with LLMs

arXiv 2508.18533 ↗First posted 25 Aug 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Procedural Content Generation for 3D game levels faces challenges in balancing spatial coherence, navigational functionality, and adaptable gameplay progression across multi-floor environments. This paper introduces a novel framework for generating such levels, centered on the offline, LLM-assisted construction of reusable databases for architectural components (facilities and room templates) and gameplay mechanic elements. Our multi-phase pipeline assembles levels by: (1) selecting and arranging instances from the Room Database to form a multi-floor global structure with an inherent topological order; (2) optimizing the internal layout of facilities for each room based on predefined constraints from the Facility Database; and (3) integrating progression-based gameplay mechanics by placing components from a Mechanics Database according to their topological and spatial rules. A subsequent two-phase repair system ensures navigability. This approach combines modular, database-driven design with constraint-based optimization, allowing for systematic control over level structure and the adaptable pacing of gameplay elements. Initial experiments validate the framework's ability in generating diverse, navigable 3D environments and its capability to simulate distinct gameplay pacing strategies through simple parameterization. This research advances PCG by presenting a scalable, database-centric foundation for the automated generation of complex 3D levels with configurable gameplay progression.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 27 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

8 of 27 references.

References · 8

  1. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
  2. 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
  3. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  4. 2020Deep Learning for Procedural Content Generationcited by 73
  5. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 59
  6. 2023ControlRoom3D: Room Generation using Semantic Proxy Roomscited by 54
  7. 2024Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketchescited by 21
  8. 2023PlotMap: Automated Layout Design for Building Game Worldscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.