Word2Minecraft: Generating 3D Game Levels through Large Language Models

2025-03-18

AI Summary

This work introduces the first end-to-end “narrative-to-Minecraft-level” generation framework, addressing the challenge of automatically transforming structured narratives—comprising protagonist goals, antagonist challenges, and environmental settings—into spatially coherent, gameplay-feasible, and aesthetically harmonious 3D playable levels. Methodologically, we design a structured prompt engineering scheme coupled with explicit spatial constraint modeling for level generation; propose an adaptive scaling algorithm to ensure spatial consistency across generated levels; and establish a joint optimization mechanism balancing narrative logic, gameplay viability, and visual fidelity. Evaluations—combining automated metrics and human assessment across multiple dimensions—employ GPT-4-Turbo and GPT-4o-Mini. Results show GPT-4-Turbo significantly improves narrative coherence and player-goal satisfaction, while generated levels achieve high map enjoyability. The implementation is publicly available.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements-such as protagonist goals, antagonist challenges, and environmental settings-into game levels with both spatial and gameplay constraints. We introduce a flexible framework that allows for the customization of story complexity, enabling dynamic level generation. The system employs a scaling algorithm to maintain spatial consistency while adapting key game elements. We evaluate Word2Minecraft using both metric-based and human-based methods. Our results show that GPT-4-Turbo outperforms GPT-4o-Mini in most areas, including story coherence and objective enjoyment, while the latter excels in aesthetic appeal. We also demonstrate the system' s ability to generate levels with high map enjoyment, offering a promising step forward in the intersection of story generation and game design. We open-source the code at https://github.com/JMZ-kk/Word2Minecraft/tree/word2mc_v0

Problem

• Generating Minecraft levels from structured stories using LLMs
• Transforming narrative elements into spatially consistent game levels
• Customizing story complexity for dynamic level generation

Innovation

• Leverages LLMs for Minecraft level generation
• Transforms narrative elements into spatial constraints
• Customizable framework for dynamic story complexity