Zero-shot 3D Map Generation with LLM Agents: A Dual-Agent Architecture for Procedural Content Generation

TL;DR

This paper introduces a dual-agent LLM system for zero-shot procedural 3D map generation, enabling natural language control and iterative refinement without task-specific training.

Contribution

It presents a novel dual-agent architecture that leverages off-the-shelf LLMs for zero-shot parameter configuration in 3D map generation, bypassing the need for training.

Findings

Outperforms single-agent baselines in generating diverse 3D maps

Produces structurally valid environments from natural language descriptions

Establishes a new benchmark for instruction-following in PCG

Abstract

Procedural Content Generation (PCG) offers scalable methods for algorithmically creating complex, customizable worlds. However, controlling these pipelines requires the precise configuration of opaque technical parameters. We propose a training-free architecture that utilizes LLM agents for zero-shot PCG parameter configuration. While Large Language Models (LLMs) promise a natural language interface for PCG tools, off-the-shelf models often fail to bridge the semantic gap between abstract user instructions and strict parameter specifications. Our system pairs an Actor agent with a Critic agent, enabling an iterative workflow where the system autonomously reasons over tool parameters and refines configurations to progressively align with human design preferences. We validate this approach on the generation of various 3D maps, establishing a new benchmark for instruction-following in PCG. Experiments demonstrate that our approach outperforms single-agent baselines, producing diverse and structurally valid environments from natural language descriptions. These results demonstrate that off-the-shelf LLMs can be effectively repurposed as generalized agents for arbitrary PCG tools. By shifting the burden from model training to architectural reasoning, our method offers a scalable framework for mastering complex software without task-specific fine-tuning.