World Craft: Agentic Framework to Create Visualizable Worlds via Text
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915760345972736 |
|---|---|
| author | Sun, Jianwen Feng, Yukang Ying, Kaining Li, Chuanhao Li, Zizhen Zhang, Fanrui Ai, Jiaxin Chang, Yifan Dai, Yu Huang, Yifei Zhang, Kaipeng |
| author_facet | Sun, Jianwen Feng, Yukang Ying, Kaining Li, Chuanhao Li, Zizhen Zhang, Fanrui Ai, Jiaxin Chang, Yifan Dai, Yu Huang, Yifei Zhang, Kaipeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09150 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | World Craft: Agentic Framework to Create Visualizable Worlds via Text Sun, Jianwen Feng, Yukang Ying, Kaining Li, Chuanhao Li, Zizhen Zhang, Fanrui Ai, Jiaxin Chang, Yifan Dai, Yu Huang, Yifei Zhang, Kaipeng Human-Computer Interaction 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. |
| title | World Craft: Agentic Framework to Create Visualizable Worlds via Text |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.09150 |