World Craft: Agentic Framework to Create Visualizable Worlds via Text

2026-01-14

AI Summary

This work addresses the challenge non-programming users face in creating executable, visual AI simulation environments through natural language. The authors propose an agent-based framework that automatically generates AI Town–like environments from user-provided textual descriptions, featuring a structured scene construction module (World Scaffold) and a multi-agent intent interpretation module (World Guild). Innovatively, the approach introduces a structured world-generation protocol tailored for non-expert users, integrates a multi-agent collaborative parsing mechanism with a reverse-engineered error-correction dataset, and incorporates spatial knowledge enhancement techniques. Experimental results demonstrate that the method significantly outperforms code-centric agents such as Cursor and Antigravity, as well as large language models including Qwen3 and Gemini-3-Pro, in both scene layout stability and narrative expressiveness, offering a scalable solution toward democratizing environment creation.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Large Language Models (LLMs) motivate generative agent simulation (e.g., AI Town) to create a ``dynamic world'', holding immense value across entertainment and research. However, for non-experts, especially those without programming skills, it isn't easy to customize a visualizable environment by themselves. In this paper, we introduce World Craft, an agentic world creation framework to create an executable and visualizable AI Town via user textual descriptions. It consists of two main modules, World Scaffold and World Guild. World Scaffold is a structured and concise standardization to develop interactive game scenes, serving as an efficient scaffolding for LLMs to customize an executable AI Town-like environment. World Guild is a multi-agent framework to progressively analyze users'intents from rough descriptions, and synthesizes required structured contents (\eg environment layout and assets) for World Scaffold . Moreover, we construct a high-quality error-correction dataset via reverse engineering to enhance spatial knowledge and improve the stability and controllability of layout generation, while reporting multi-dimensional evaluation metrics for further analysis. Extensive experiments demonstrate that our framework significantly outperforms existing commercial code agents (Cursor and Antigravity) and LLMs (Qwen3 and Gemini-3-Pro). in scene construction and narrative intent conveyance, providing a scalable solution for the democratization of environment creation.

Problem

• generative agent simulation
• visualizable world
• text-to-environment
• non-expert customization
• AI Town

Innovation

• Agentic Framework
• Visualizable World Generation
• World Scaffold
• Multi-agent Intent Analysis
• Error-correction Dataset