RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation

[2608.05714] RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.05714 (cs) [Submitted on 6 Aug 2026 ( v1 ), last revised 7 Aug 2026 (this version, v2)] Title: RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation Authors: Shuhao Yan , Changhao He , Peng Hu , Xi Peng View a PDF of the paper titled RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation, by Shuhao Yan and 3 other authors View PDF HTML (experimental) Abstract: Text-to-CAD generation translates natural-language design intent into editable and executable parametric computer-aided design (CAD) codes, reducing the expertise and effort required for manual modeling. Existing methods incorporate fixed, externally supplied, prompt-induced, or separately optimized critique mechanisms to optimize the generation process, but they do not necessarily optimize how feedback is interpreted and translated into effective corrective actions throughout the generation process. To bridge this feedback-utilization gap, we present RA-CAD (ReAct Agent for CAD), a state-aware agent that interacts with the CAD environment through a Generate--Execute--Critique--Rewrite loop. At each iteration, RA-CAD executes the current code and observes its outcome. Conditioned on the design instruction, current code, and execution feedback, the agent then generates an explicit post-execution critique as an intermediate policy action. This critique either validates the current result for termination or provides revision-oriented guidance that conditions the next rewrite. CAD Code Bootstrapping (CCB) first establishes fundamental parametric CAD coding capabilities through supervised fine-tuning. Feedback-Driven Agent Optimization (FAO) subsequently applies trajectory-level Group Relative Policy Optimization to both policy-generated code and critique sequences, assigning terminal F1 and Chamfer Distance rewards to the complete interaction trajectory. This formulation makes critique an outcome-aligned, learnable policy decision rather than an unoptimized auxiliary output. Experiments on CADFusion and Text2CAD show that RA-CAD achieves state-of-the-art execution validity and geometric quality compared with existing methods and strong proprietary language models, demonstrating the effectiveness of the proposed state-aware text-to-CAD agent. Comments: 17 pages, 7 figures Subjects: Artificial Intelligence (cs.AI) ACM classes: I.2.6; I.2.8 Cite as: arXiv:2608.05714 [cs.AI] (or arXiv:2608.05714v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.05714 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Peng Hu [ view email ] [v1] Thu, 6 Aug 2026 07:52:45 UTC (9,711 KB) [v2] Fri, 7 Aug 2026 03:42:09 UTC (9,711 KB) Full-text links: Access Paper: View a PDF of the paper titled RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation, by Shuhao Yan and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation#610024
• Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning#785144
• Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning#783554
• Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning#343552
• Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning#1130653