6 papers
TraceCAD: Trace-Guided Repair for Agentic CAD Generation
Fengxiao Fan, Jingzhe Ni, Fan Sang +5
LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We int…
CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation
Yu Liu, Jingzhe Ni, Yiming Chen +4
Large language models have made it possible to generate executable computer-aided design (CAD) programs from natural-language descriptions or images. However, existing methods repr…
MidSurfNet: Learnable Face Pairing and Interference Implicit Fields for Generalized Mid-surface Abstraction
Li Ye, Xinhang Zhou, Xingyu Yang +4
Mid-surface abstraction is essential for finite element analysis of thin-walled CAD models. Existing face pairing-based methods rely on handcrafted geometric heuristics, yet real-w…
CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent
Fengxiao Fan, Jingzhe Ni, Xiaolong Yin +6
Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from designers. To lower the entry bar…
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation an…
RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation
Xiaolong Yin, Xingyu Lu, Jiahang Shen +5
A CAD command sequence is a typical parametric design paradigm in 3D CAD systems where a model is constructed by overlaying 2D sketches with operations such as extrusion, revolutio…