PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models
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_ | 1866918460926197760 |
|---|---|
| author | An, Jiyuan Zhao, Jiachen Chen, Fan Yang, Liner Liu, Zhenghao Wang, Hongyan An, Weihua Zhang, Meishan Yang, Erhong |
| author_facet | An, Jiyuan Zhao, Jiachen Chen, Fan Yang, Liner Liu, Zhenghao Wang, Hongyan An, Weihua Zhang, Meishan Yang, Erhong |
| contents | The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspired research into text-to-CAD generation. However, existing approaches typically treat generation and editing as disjoint tasks, limiting their practicality. We propose PR-CAD, a progressive refinement framework that unifies generation and editing for controllable and faithful text-to-CAD modeling. To support this, we curate a high-fidelity interaction dataset spanning the full CAD lifecycle, encompassing multiple CAD representations as well as both qualitative and quantitative descriptions. The dataset systematically defines the types of edit operations and generates highly human-like interaction data. Building on a CAD representation tailored for LLMs, we propose a reinforcement learning-enhanced reasoning framework that integrates intent understanding, parameter estimation, and precise edit localization into a single agent. This enables an "all-in-one" solution for both design creation and refinement. Extensive experiments demonstrate strong mutual reinforcement between generation and editing tasks, and across qualitative and quantitative modalities. On public benchmarks, PR-CAD achieves state-of-the-art controllability and faithfulness in both generation and refinement scenarios, while also proving user-friendly and significantly improving CAD modeling efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19773 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models An, Jiyuan Zhao, Jiachen Chen, Fan Yang, Liner Liu, Zhenghao Wang, Hongyan An, Weihua Zhang, Meishan Yang, Erhong Computation and Language Artificial Intelligence The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspired research into text-to-CAD generation. However, existing approaches typically treat generation and editing as disjoint tasks, limiting their practicality. We propose PR-CAD, a progressive refinement framework that unifies generation and editing for controllable and faithful text-to-CAD modeling. To support this, we curate a high-fidelity interaction dataset spanning the full CAD lifecycle, encompassing multiple CAD representations as well as both qualitative and quantitative descriptions. The dataset systematically defines the types of edit operations and generates highly human-like interaction data. Building on a CAD representation tailored for LLMs, we propose a reinforcement learning-enhanced reasoning framework that integrates intent understanding, parameter estimation, and precise edit localization into a single agent. This enables an "all-in-one" solution for both design creation and refinement. Extensive experiments demonstrate strong mutual reinforcement between generation and editing tasks, and across qualitative and quantitative modalities. On public benchmarks, PR-CAD achieves state-of-the-art controllability and faithfulness in both generation and refinement scenarios, while also proving user-friendly and significantly improving CAD modeling efficiency. |
| title | PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.19773 |