TY - GEN
T1 - AutoUE
T2 - 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
AU - Yin, Lei
AU - Cheng, Wentao
AU - Qin, Zhida
AU - Huang, Tianyu
AU - Li, Yidong
AU - Ding, Gangyi
N1 - Publisher Copyright:
© 2026 Association for Computational Linguistics.
PY - 2026
Y1 - 2026
N2 - Automatically generating 3D games in commercial game engines remains a non-trivial challenge, as it involves complex engine-related workflows for generating assets such as scenes, blueprints, and code. To address this challenge, we propose a novel multi-agent system, AutoUE, which coordinates multiple agents to end-to-end generate 3D games, covering model retrieval, scene generation, gameplay and interaction code synthesis, and automated game testing for evaluation. In order to mitigate tool-use hallucinations in LLMs, we introduce a retrieval-augmented generation mechanism that grounds agents with relevant UE tool documentation. Additionally, we incorporate game design patterns and engine constraints into the code generation process to ensure the generation of correct and robust code. Furthermore, we design an automated play-testing pipeline that generates and executes runtime test commands, enabling systematic evaluation of dynamic behaviors. Finally, we construct a game generation dataset and conduct a series of experiments that demonstrate AutoUE’s ability to generate 3D games end-to-end, and validate the effectiveness of these designs.1
AB - Automatically generating 3D games in commercial game engines remains a non-trivial challenge, as it involves complex engine-related workflows for generating assets such as scenes, blueprints, and code. To address this challenge, we propose a novel multi-agent system, AutoUE, which coordinates multiple agents to end-to-end generate 3D games, covering model retrieval, scene generation, gameplay and interaction code synthesis, and automated game testing for evaluation. In order to mitigate tool-use hallucinations in LLMs, we introduce a retrieval-augmented generation mechanism that grounds agents with relevant UE tool documentation. Additionally, we incorporate game design patterns and engine constraints into the code generation process to ensure the generation of correct and robust code. Furthermore, we design an automated play-testing pipeline that generates and executes runtime test commands, enabling systematic evaluation of dynamic behaviors. Finally, we construct a game generation dataset and conduct a series of experiments that demonstrate AutoUE’s ability to generate 3D games end-to-end, and validate the effectiveness of these designs.1
UR - https://www.scopus.com/pages/publications/105053542598
M3 - Conference contribution
AN - SCOPUS:105053542598
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 2341
EP - 2364
BT - 64th Annual Meeting of the Association for Computational Linguistics, Findings of the Association for Computational Linguistics
A2 - Liakata, Maria
A2 - Moreira, Viviane P.
A2 - Zhang, Jiajun
A2 - Jurgens, David
PB - Association for Computational Linguistics (ACL)
Y2 - 2 July 2026 through 7 July 2026
ER -