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

2025-08-25

AI Summary

Addressing the challenge of simultaneously ensuring spatial coherence, navigability, and gameplay-adaptive progression in multi-floor 3D level generation, this paper proposes a modular, stage-wise procedural generation framework. The method leverages large language models (LLMs) to assist in constructing reusable architectural components and gameplay mechanism libraries; integrates parametric pacing control, topological rule constraints, a two-stage structural repair mechanism, and spatial layout optimization algorithms to enable structured and controllable level synthesis. Experimental evaluation demonstrates that the framework consistently generates diverse, navigable, and rhythm-aware multi-floor 3D levels—adapting effectively to distinct gameplay pacing strategies. Quantitative and qualitative assessments confirm significant improvements over baseline approaches in playability, generation quality, and adaptability across varied design requirements.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

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.

Problem

• Generating 3D game levels with spatial coherence and navigational functionality
• Balancing adaptable gameplay progression across multi-floor environments
• Automating creation of complex 3D levels with configurable gameplay elements

Innovation

• LLM-assisted reusable database construction
• Multi-phase pipeline with topological ordering
• Constraint-based optimization for navigability