一句话：提出约束表达型中间表示驱动的3D软件合成，支持元素级修改并处理空间与语义约束。
三维图形用户界面正从传统2D界面转向空间化3D环境，但现有工作多集中于2D软件生成，3D软件生成仍探索不足。当前3D生成方法通常把整个3D环境作为整体生成，难以对其中特定元素进行修改，也难以处理真实世界中复杂的空间与语义约束。该论文提出由约束表达型中间表示（constraint-expressive intermediate representation）驱动的3D软件合成方法，旨在通过具有约束表达能力的IR支持3D软件的结构化生成与细粒度修改。摘要未报告具体实现细节、实验设置或定量结果，因此无法从摘要判断其评估方式与效果。
Graphical user interface (UI) software has undergone a fundamental transformation from traditional 2D interfaces to spatial 3D environments. While existing work has made remarkable success in 2D software generation, 3D software generation still remains underexplored. Current methods for 3D software generation usually generate 3D environment as a whole and cannot modify specific elements. Furthermore, these methods struggle to handle the complex spatial and semantic constraints inherent in the real world.
@inproceedings{paperbot11675,
title = {3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation},
author = {Shuqing Li and Anson Y. Lam and Yun Peng and Wenxuan Wang and Michael R. Lyu},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787812}
}