---
title: "AutoUE — paper by Yin et al. (2026) — summary and ideas"
description: "Several design choices target reliability: Retrieval over UE tool documentation curbs hallucinated tool usage. 35 references."
authors: ["Lei Yin", "Wentao Cheng", "Zhida Qin", "Tianyu Huang", "Yidong Li", "Gangyi Ding"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.111/"
doi: "10.18653/v1/2026.findings-acl.111"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yin-2026-autoue-automated-generation-3d-games/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yin-2026-autoue-automated-generation-3d-games/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/) / AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems

# AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems

**Authors:** Lei Yin, Wentao Cheng, Zhida Qin, Tianyu Huang, Yidong Li and Gangyi Ding · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.111/) · [PDF](https://aclanthology.org/2026.findings-acl.111.pdf) · [DOI 10.18653/v1/2026.findings-acl.111](https://doi.org/10.18653/v1/2026.findings-acl.111) · [OpenAlex](https://openalex.org/W7166829489)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Producing a complete, playable 3D game inside a commercial engine is hard to automate. The work spans scenes, blueprints and code across tightly coupled engine workflows, and earlier LLM-based efforts mostly addressed only one piece, such as scene layout or script generation. AutoUE is a multi-agent system for Unreal Engine (UE) that chains five LLM agents, each feeding the next:

1. model retrieval
2. scene generation via UE's Procedural Content Generation (PCG) graphs
3. modular C++ gameplay code
4. interactive object logic
5. automated play-testing

The agents talk to the engine through a Model Context Protocol (MCP) layer. Several design choices target reliability:
- Retrieval over UE tool documentation curbs hallucinated tool usage.
- Game design patterns and engine constraints guide code generation.
- Runtime test commands are generated and executed so that dynamic behaviour can be scored without human inspection.

The authors also built a 20-task benchmark, PlayGen-20. On it, AutoUE produces better scenes than prior approaches. Ablations show that the PCG patterns, the retrieved node knowledge and the code-design elements are each necessary for valid graphs and compilable code. This makes the system a reusable basis for end-to-end in-engine game generation.

## Key points
- **Retrieval database:** the model retrieval agent searches an embedding database of 858K 3D models. Code is available at github.com/Pluto156/AutoUE.
- **PCG graph ablation:** the full system reaches 100% node creation, parameter filling and pin connection success, with an LLM-judged S_PCG of 8.42. Each removed component causes a drop:
  - Without patterns: S_Node falls to 79.6% and S_Pin to 64.0%.
  - Without parameter documentation: S_Param falls to 55.2%.
  - Without connection documentation: S_Pin falls to 80.4% and S_PCG to 5.02.
- **Gameplay code ablation:** if the system lacks the module-dependency information, the code templates, or the engine constraints, compilation fails in every case. The overall GCS drops from 7.38 to roughly 2.44–2.48.
- **Limitations:** there is no comparison with DreamGarden, which is not open-source. The 20-task benchmark may not reflect real-world development complexity.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 626 works · [🖥️ Computer Graphics and Computer-Aided Design](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-graphics-and-computer-aided-design/) · 16 works

## Cite

Cite as: Lei Yin, Wentao Cheng, Zhida Qin, Tianyu Huang, Yidong Li and Gangyi Ding. 2026. AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yin2026autoue,
  title = {{AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems}},
  author = {Lei Yin, Wentao Cheng, Zhida Qin, Tianyu Huang, Yidong Li and Gangyi Ding},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.111},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.111}
}
```

- [← previous AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs](https://md.research.elamur.ai/free/en/papers/lyu-2026-autotaskeval-domain-specific-fine-grained/)
- [next → AVA: Attentive VLM Agent for Mastering StarCraft II](https://md.research.elamur.ai/free/en/papers/ma-2026-ava-attentive-vlm-agent-mastering/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/)

## References

35 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jake Bruce, Michael D Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, and 1 others. 2024. Genie: Generative interactive environments. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Jake+Bruce%2C+Michael+D+Dennis%2C+Ashley+Edwards%2C+Jack+Parker%2DHolder%2C+Yuge+Shi%2C+Edward+Hughes%2C+Matthew+Lai%2C+Aditi+Mavalankar%2C+Richie+Steigerwald%2C+Chris+Apps%2C+and+1+others%2E+2024%2E+Genie%3A+Generative+interact)
2. Steph Buongiorno, Lawrence Klinkert, Zixin Zhuang, Tanishq Chawla, and Corey Clark. 2024. Pangea: procedural artificial narrative using generative ai for turn-based, role-playing video games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volu… [find](https://scholar.google.com/scholar?q=Steph+Buongiorno%2C+Lawrence+Klinkert%2C+Zixin+Zhuang%2C+Tanishq+Chawla%2C+and+Corey+Clark%2E+2024%2E+Pangea%3A+procedural+artificial+narrative+using+generative+ai+for+turn%2Dbased%2C+role%2Dplaying+video+games%2E+In+Proce)
3. Haoxuan Che, Xuanhua He, Quande Liu, Cheng Jin, and Hao Chen. 2025. Gamegen-x: Interactive open-world game video generation. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Haoxuan+Che%2C+Xuanhua+He%2C+Quande+Liu%2C+Cheng+Jin%2C+and+Hao+Chen%2E+2025%2E+Gamegen%2Dx%3A+Interactive+open%2Dworld+game+video+generation%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
4. Peng Chen, Pi Bu, Jun Song, Yuan Gao, and Bo Zheng. 2024. Can vlms play action role-playing games? take black myth wukong as a study case. In NeurIPS 2024 Workshop on Open-World Agents. [find](https://scholar.google.com/scholar?q=Peng+Chen%2C+Pi+Bu%2C+Jun+Song%2C+Yuan+Gao%2C+and+Bo+Zheng%2E+2024%2E+Can+vlms+play+action+role%2Dplaying+games%3F+take+black+myth+wukong+as+a+study+case%2E+In+NeurIPS+2024+Workshop+on+Open%2DWorld+Agents%2E)
5. Marc-Alexandre Côté, Akos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, and 1 others. 2018. [Textworld: A learning environment for text-based games](https://md.research.elamur.ai/free/en/papers/cote-2018-textworld-learning-environment-text-based/). In Workshop on Computer Games, pages 41–75. Springer.
6. Shiqi Dai, Xuanyu Zhu, Naiqi Li, Tao Dai, and Zhi Wang. 2024. Procedural level generation with diffusion models from a single example. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 10021–10029. [find](https://scholar.google.com/scholar?q=Shiqi+Dai%2C+Xuanyu+Zhu%2C+Naiqi+Li%2C+Tao+Dai%2C+and+Zhi+Wang%2E+2024%2E+Procedural+level+generation+with+diffusion+models+from+a+single+example%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C)
7. Sam Earle, Samyak Parajuli, and Andrzej Banburski-Fahey. 2025. Dreamgarden: A designer assistant for growing games from a single prompt. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pages 1–19. [find](https://scholar.google.com/scholar?q=Sam+Earle%2C+Samyak+Parajuli%2C+and+Andrzej+Banburski%2DFahey%2E+2025%2E+Dreamgarden%3A+A+designer+assistant+for+growing+games+from+a+single+prompt%2E+In+Proceedings+of+the+2025+CHI+Conference+on+Human+Factors+in+C)
8. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Peiyi+Wang%2C+Qihao+Zhu%2C+Runxin+Xu%2C+Ruoyu+Zhang%2C+Shirong+Ma%2C+Xiao+Bi%2C+and+1+others%2E+2025%2E+Deepseekr1+incentivizes+reasoning+in+llms+through+reinforceme)
9. Amna Hassan. 2025. Automated unity game template generation from gdds via nlp and multi-modal llms. arXiv preprint arXiv:2509.08847. — [arXiv:2509.08847](https://arxiv.org/abs/2509.08847) [find](https://scholar.google.com/scholar?q=Amna+Hassan%2E+2025%2E+Automated+unity+game+template+generation+from+gdds+via+nlp+and+multi%2Dmodal+llms%2E+arXiv+preprint+arXiv%3A2509%2E08847%2E+%E2%80%94+%5BarXiv%3A2509%2E08847%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2509%2E08847%29)
10. Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, and Xingdi Yuan. 2020. Interactive fiction games: A colossal adventure. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 7903–7910. [find](https://scholar.google.com/scholar?q=Matthew+Hausknecht%2C+Prithviraj+Ammanabrolu%2C+Marc%2DAlexandre+C%C3%B4t%C3%A9%2C+and+Xingdi+Yuan%2E+2020%2E+Interactive+fiction+games%3A+A+colossal+adventure%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligenc)
11. Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Satoshi Ohshima, and Takahiro Katagiri. 2025. 3dify: a framework for procedural 3d-cg generation assisted by llms using mcp and rag. arXiv preprint arXiv:2510.04536. — [arXiv:2510.04536](https://arxiv.org/abs/2510.04536) [find](https://scholar.google.com/scholar?q=Shun%2Dichiro+Hayashi%2C+Daichi+Mukunoki%2C+Tetsuya+Hoshino%2C+Satoshi+Ohshima%2C+and+Takahiro+Katagiri%2E+2025%2E+3dify%3A+a+framework+for+procedural+3d%2Dcg+generation+assisted+by+llms+using+mcp+and+rag%2E+arXiv+prepri)
12. Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840– 6851. [find](https://scholar.google.com/scholar?q=Jonathan+Ho%2C+Ajay+Jain%2C+and+Pieter+Abbeel%2E+2020%2E+Denoising+diffusion+probabilistic+models%2E+Advances+in+neural+information+processing+systems%2C+33%3A6840%E2%80%93+6851%2E)
13. Chengpeng Hu, Yunlong Zhao, and Jialin Liu. 2024. Game generation via large language models. In 2024 IEEE Conference on Games (CoG), pages 1–4. IEEE. [find](https://scholar.google.com/scholar?q=Chengpeng+Hu%2C+Yunlong+Zhao%2C+and+Jialin+Liu%2E+2024%2E+Game+generation+via+large+language+models%2E+In+2024+IEEE+Conference+on+Games+%28CoG%29%2C+pages+1%E2%80%934%2E+IEEE%2E)
14. Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, and Tsung-Yi Lin. 2023. Magic3d: High-resolution text-to-3d content creation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 300–309. [find](https://scholar.google.com/scholar?q=Chen%2DHsuan+Lin%2C+Jun+Gao%2C+Luming+Tang%2C+Towaki+Takikawa%2C+Xiaohui+Zeng%2C+Xun+Huang%2C+Karsten+Kreis%2C+Sanja+Fidler%2C+Ming%2DYu+Liu%2C+and+Tsung%2DYi+Lin%2E+2023%2E+Magic3d%3A+High%2Dresolution+text%2Dto%2D3d+content+creation%2E+)
15. Mahdi Farrokhi Maleki and Richard Zhao. 2024. Procedural content generation in games: A survey with insights on emerging llm integration. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 20, pages 167–178. [find](https://scholar.google.com/scholar?q=Mahdi+Farrokhi+Maleki+and+Richard+Zhao%2E+2024%2E+Procedural+content+generation+in+games%3A+A+survey+with+insights+on+emerging+llm+integration%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligen)
16. Luiza Martins de Freitas Cintra, Elisa Ayumi Masasi de Oliveira, Rafael Teixeira Sousa, Valdemar Vicente Graciano, Arlindo Galvão, Gustavo Webster, and Sofia Larissa da Costa Paiva. 2025. An llm-enhanced framework for bridging simulators and game engines towards realistic 3d simulations. In Proceedi… [find](https://scholar.google.com/scholar?q=Luiza+Martins+de+Freitas+Cintra%2C+Elisa+Ayumi+Masasi+de+Oliveira%2C+Rafael+Teixeira+Sousa%2C+Valdemar+Vicente+Graciano%2C+Arlindo+Galv%C3%A3o%2C+Gustavo+Webster%2C+and+Sofia+Larissa+da+Costa+Paiva%2E+2025%2E+An+llm%2Denhan)
17. Dani Valevski, Yaniv Leviathan, Moab Arar, and Shlomi Fruchter. 2025. Diffusion models are real-time game engines. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Dani+Valevski%2C+Yaniv+Leviathan%2C+Moab+Arar%2C+and+Shlomi+Fruchter%2E+2025%2E+Diffusion+models+are+real%2Dtime+game+engines%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
18. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
19. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2024. Voyager: An open-ended embodied agent with large language models. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+2024%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+Transactions+on+M)
20. Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2023. Dreamfusion: Text-to-3d using 2d diffusion. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ben+Poole%2C+Ajay+Jain%2C+Jonathan+T+Barron%2C+and+Ben+Mildenhall%2E+2023%2E+Dreamfusion%3A+Text%2Dto%2D3d+using+2d+diffusion%2E+In+The+Eleventh+International+Conference+on+Learning+Representations%2E)
21. Alexander Raistrick, Lahav Lipson, Zeyu Ma, Lingjie Mei, Mingzhe Wang, Yiming Zuo, Karhan Kayan, Hongyu Wen, Beining Han, Yihan Wang, and 1 others. 2023. Infinite photorealistic worlds using procedural generation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,… [find](https://scholar.google.com/scholar?q=Alexander+Raistrick%2C+Lahav+Lipson%2C+Zeyu+Ma%2C+Lingjie+Mei%2C+Mingzhe+Wang%2C+Yiming+Zuo%2C+Karhan+Kayan%2C+Hongyu+Wen%2C+Beining+Han%2C+Yihan+Wang%2C+and+1+others%2E+2023%2E+Infinite+photorealistic+worlds+using+procedura)
22. Shu Wang, Lei Ji, Renxi Wang, Wenxiao Zhao, Haokun Liu, Yifan Hou, and Ying Nian Wu. 2025. Explore the reasoning capability of llms in the chess testbed. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Tech… [find](https://scholar.google.com/scholar?q=Shu+Wang%2C+Lei+Ji%2C+Renxi+Wang%2C+Wenxiao+Zhao%2C+Haokun+Liu%2C+Yifan+Hou%2C+and+Ying+Nian+Wu%2E+2025%2E+Explore+the+reasoning+capability+of+llms+in+the+chess+testbed%2E+In+Proceedings+of+the+2025+Conference+of+the+N)
23. Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Shawn Ma, and Yitao Liang. 2023. Describe, explain, plan and select: interactive planning with llms enables open-world multi-task agents. Advances in Neural Information Processing Systems, 36:34153–34189. [find](https://scholar.google.com/scholar?q=Zihao+Wang%2C+Shaofei+Cai%2C+Guanzhou+Chen%2C+Anji+Liu%2C+Xiaojian+Shawn+Ma%2C+and+Yitao+Liang%2E+2023%2E+Describe%2C+explain%2C+plan+and+select%3A+interactive+planning+with+llms+enables+open%2Dworld+multi%2Dtask+agents%2E+Adv)
24. SongTang SongTang, Kaiyong Zhao, Lei Wang, Yuliang Li, Xuebo Liu, Junyi Zou, Qiang Wang, and Xiaowen Chu. 2025. Unrealllm: Towards highly controllable and interactable 3d scene generation by llm-powered procedural content generation. In Findings of the Association for Computational Linguistics: ACL… [find](https://scholar.google.com/scholar?q=SongTang+SongTang%2C+Kaiyong+Zhao%2C+Lei+Wang%2C+Yuliang+Li%2C+Xuebo+Liu%2C+Junyi+Zou%2C+Qiang+Wang%2C+and+Xiaowen+Chu%2E+2025%2E+Unrealllm%3A+Towards+highly+controllable+and+interactable+3d+scene+generation+by+llm%2Dpower)
25. Kazuki Wayama, Tomoyuki Yokogawa, Sousuke Amasaki, Hirohisa Aman, and Kazutami Arimoto. 2022. Verifying game logic in unreal engine 5 blueprint visual scripting system using model checking. In Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, pages 1–8. [find](https://scholar.google.com/scholar?q=Kazuki+Wayama%2C+Tomoyuki+Yokogawa%2C+Sousuke+Amasaki%2C+Hirohisa+Aman%2C+and+Kazutami+Arimoto%2E+2022%2E+Verifying+game+logic+in+unreal+engine+5+blueprint+visual+scripting+system+using+model+checking%2E+In+Proceed)
26. Shyam Sudhakaran, Miguel González-Duque, Matthias Freiberger, Claire Glanois, Elias Najarro, and Sebastian Risi. 2023. Mariogpt: Open-ended text2level generation through large language models. Advances in Neural Information Processing Systems, 36:54213– 54227. [find](https://scholar.google.com/scholar?q=Shyam+Sudhakaran%2C+Miguel+Gonz%C3%A1lez%2DDuque%2C+Matthias+Freiberger%2C+Claire+Glanois%2C+Elias+Najarro%2C+and+Sebastian+Risi%2E+2023%2E+Mariogpt%3A+Open%2Dended+text2level+generation+through+large+language+models%2E+Advance)
27. Yongzhi Xu, Yonhon Ng, Yifu Wang, Inkyu Sa, Yunfei Duan, Yang Li, Pan Ji, and Hongdong Li. 2024. Sketch2scene: Automatic generation of interactive 3d game scenes from user’s casual sketches. arXiv preprint arXiv:2408.04567. — [arXiv:2408.04567](https://arxiv.org/abs/2408.04567) [find](https://scholar.google.com/scholar?q=Yongzhi+Xu%2C+Yonhon+Ng%2C+Yifu+Wang%2C+Inkyu+Sa%2C+Yunfei+Duan%2C+Yang+Li%2C+Pan+Ji%2C+and+Hongdong+Li%2E+2024%2E+Sketch2scene%3A+Automatic+generation+of+interactive+3d+game+scenes+from+user%E2%80%99s+casual+sketches%2E+arXiv+pre)
28. Chunyi Sun, Junlin Han, Weijian Deng, Xinlong Wang, Zishan Qin, and Stephen Gould. 2025. 3d-gpt: Procedural 3d modeling with large language models. In 2025 International Conference on 3D Vision (3DV), pages 1253–1263. IEEE. [find](https://scholar.google.com/scholar?q=Chunyi+Sun%2C+Junlin+Han%2C+Weijian+Deng%2C+Xinlong+Wang%2C+Zishan+Qin%2C+and+Stephen+Gould%2E+2025%2E+3d%2Dgpt%3A+Procedural+3d+modeling+with+large+language+models%2E+In+2025+International+Conference+on+3D+Vision+%283DV%29%2C)
29. Yuqian Sun, Zhouyi Li, Ke Fang, Chang Hee Lee, and Ali Asadipour. 2023. Language as reality: a co-creative storytelling game experience in 1001 nights using generative ai. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 19, pages 425–434… [find](https://scholar.google.com/scholar?q=Yuqian+Sun%2C+Zhouyi+Li%2C+Ke+Fang%2C+Chang+Hee+Lee%2C+and+Ali+Asadipour%2E+2023%2E+Language+as+reality%3A+a+co%2Dcreative+storytelling+game+experience+in+1001+nights+using+generative+ai%2E+In+Proceedings+of+the+AAAI+C)
30. Weihao Tan, Xiangyang Li, Yunhao Fang, Heyuan Yao, Shi Yan, Hao Luo, Tenglong Ao, Huihui Li, Hongbin Ren, Bairen Yi, and 1 others. 2025. Lumine: An open recipe for building generalist agents in 3d open worlds. arXiv preprint arXiv:2511.08892. — [arXiv:2511.08892](https://arxiv.org/abs/2511.08892) [find](https://scholar.google.com/scholar?q=Weihao+Tan%2C+Xiangyang+Li%2C+Yunhao+Fang%2C+Heyuan+Yao%2C+Shi+Yan%2C+Hao+Luo%2C+Tenglong+Ao%2C+Huihui+Li%2C+Hongbin+Ren%2C+Bairen+Yi%2C+and+1+others%2E+2025%2E+Lumine%3A+An+open+recipe+for+building+generalist+agents+in+3d+ope)
31. Graham Todd, Alexander G Padula, Matthew Stephenson, Éric Piette, Dennis J Soemers, and Julian Togelius. 2024. Gavel: Generating games via evolution and language models. Advances in Neural Information Processing Systems, 37:110723–110745. [find](https://scholar.google.com/scholar?q=Graham+Todd%2C+Alexander+G+Padula%2C+Matthew+Stephenson%2C+%C3%89ric+Piette%2C+Dennis+J+Soemers%2C+and+Julian+Togelius%2E+2024%2E+Gavel%3A+Generating+games+via+evolution+and+language+models%2E+Advances+in+Neural+Information)
32. Runxin Yang, Yuxuan Wan, Shuqing Li, and Michael R Lyu. 2025. 90% faster, 100% code-free: Mllm-driven zero-code 3d game development. arXiv preprint arXiv:2509.26161. — [arXiv:2509.26161](https://arxiv.org/abs/2509.26161) [find](https://scholar.google.com/scholar?q=Runxin+Yang%2C+Yuxuan+Wan%2C+Shuqing+Li%2C+and+Michael+R+Lyu%2E+2025%2E+90%25+faster%2C+100%25+code%2Dfree%3A+Mllm%2Ddriven+zero%2Dcode+3d+game+development%2E+arXiv+preprint+arXiv%3A2509%2E26161%2E+%E2%80%94+%5BarXiv%3A2509%2E26161%5D%28https%3A%2F%2Farxiv)
33. Hong-Xing Yu, Haoyi Duan, Junhwa Hur, Kyle Sargent, Michael Rubinstein, William T Freeman, Forrester Cole, Deqing Sun, Noah Snavely, Jiajun Wu, and 1 others. 2024. Wonderjourney: Going from anywhere to everywhere. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,… [find](https://scholar.google.com/scholar?q=Hong%2DXing+Yu%2C+Haoyi+Duan%2C+Junhwa+Hur%2C+Kyle+Sargent%2C+Michael+Rubinstein%2C+William+T+Freeman%2C+Forrester+Cole%2C+Deqing+Sun%2C+Noah+Snavely%2C+Jiajun+Wu%2C+and+1+others%2E+2024%2E+Wonderjourney%3A+Going+from+anywhere+t)
34. Yibo Zhang, Li Zhang, Rui Ma, and Nan Cao. 2025. Texverse: A universe of 3d objects with high-resolution textures. arXiv preprint arXiv:2508.10868. — [arXiv:2508.10868](https://arxiv.org/abs/2508.10868) [find](https://scholar.google.com/scholar?q=Yibo+Zhang%2C+Li+Zhang%2C+Rui+Ma%2C+and+Nan+Cao%2E+2025%2E+Texverse%3A+A+universe+of+3d+objects+with+high%2Dresolution+textures%2E+arXiv+preprint+arXiv%3A2508%2E10868%2E+%E2%80%94+%5BarXiv%3A2508%2E10868%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2508%2E1086)
35. Mengqi Zhou, Yuxi Wang, Jun Hou, Shougao Zhang, Yiwei Li, Chuanchen Luo, Junran Peng, and Zhaoxiang Zhang. 2025. Scenex: Procedural controllable large-scale scene generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 10806–10814. [find](https://scholar.google.com/scholar?q=Mengqi+Zhou%2C+Yuxi+Wang%2C+Jun+Hou%2C+Shougao+Zhang%2C+Yiwei+Li%2C+Chuanchen+Luo%2C+Junran+Peng%2C+and+Zhaoxiang+Zhang%2E+2025%2E+Scenex%3A+Procedural+controllable+large%2Dscale+scene+generation%2E+In+Proceedings+of+the+AAA)

*Updated 2 November 2026*