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

• URL: http://arxiv.org/abs/2608.05714v1
• Date: Thu, 06 Aug 2026 07:52:45 GMT
• Title: RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation
• Abstract summary: RA-CAD is a state-aware agent that interacts with the CAD environment through a Generate--Execute--Critique--Rewrite loop.<n>The agent generates an explicit post-execution critique as an intermediate policy action.<n> RA-CAD achieves state-of-the-art execution validity and geometric quality compared with existing methods.
• Score: 25.137571635322896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views [35.452775950511935]
  IterCAD is an iterative framework that reformulates orthographic-view-to-CAD generation as a progressive program repair process.<n>IterCAD repeatedly analyzes the current CAD result, reasons about its discrepancy with the target views, and explicitly decides whether to REVISE the code or STOP the refinement process.<n>IterCAD consistently improves code executability and geometric fidelity over strong one-shot baselines.
  arXiv  Detail & Related papers  (2026-08-25T03:22:10Z)
• CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation [13.468378066479497]
  We present CADIR, an agent-friendly executable intermediate representation for CAD generation and cross-backend editing.<n>Built on the OCCT geometry kernel via OCP, CADIR provides explicit, compositional modeling operations and fine-grained execution diagnostics.
  arXiv  Detail & Related papers  (2026-08-01T23:07:08Z)
• IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing [31.86100517851177]
  IterCAD is a unified multimodal agent framework for closed-loop, interactive CAD generation and editing.<n>It achieves highly competitive performance across multiple benchmarks, significantly outperforming existing approaches in both code executability and geometric precision.
  arXiv  Detail & Related papers  (2026-06-11T13:53:21Z)
• CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences [51.86576932800981]
  We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales.<n>CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types.<n>We develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification.
  arXiv  Detail & Related papers  (2026-05-30T23:37:55Z)
• PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models [32.278474349549704]
  PR-CAD is a progressive refinement framework that unifies generation and editing for controllable and faithful text-to-CAD modeling.<n>The dataset systematically defines the types of edit operations and generates highly human-like interaction data.<n>On public benchmarks, PR-CAD achieves state-of-the-art controllability and faithfulness in both generation and refinement scenarios.
  arXiv  Detail & Related papers  (2026-03-27T12:13:20Z)
• Agentic Planning with Reasoning for Image Styling via Offline RL [66.10749901925941]
  Direct prompt-based editing fails on complex transformations because vague and subjective prompts often require nuanced understanding of what should be changed in the image.<n>We present a tool-based agentic RL post-training framework that addresses this through structured planning with chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2026-03-07T11:14:37Z)
• DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces [67.45867367326105]
  We propose DreamCAD, a multi-modal generative framework that directly produces editable BReps from point-level supervision.<n>DreamCAD represents each BRep as a set of parametric patches and uses a differentiable tessellation method to generate meshes.<n>DreamCAD achieves state-of-the-art performance on ABC and averse benchmarks across text, image, and point modalities.
  arXiv  Detail & Related papers  (2026-03-05T19:04:07Z)
• ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models [16.220781575918256]
  ReCAD is a reinforcement learning (RL) framework that bootstraps pretrained large models (PLMs) to generate precise parametric computer-aided design (CAD) models from multimodal inputs.<n>We employ a hierarchical primitive learning process to teach structured and compositional skills under a unified reward function.<n>ReCAD sets a new state-of-the-art in both text-to-CAD and image-to-CAD tasks, significantly improving geometric accuracy across in-distribution and out-of-distribution settings.
  arXiv  Detail & Related papers  (2025-12-06T07:12:56Z)
• From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation [47.67703214044401]
  We propose CAD-RL, a multimodal Chain-of-Thought guided reinforcement learning framework for CAD modeling code generation.<n>Our method combines Cold Start with goal-driven reinforcement learning post training using three task-specific rewards.<n>Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability.
  arXiv  Detail & Related papers  (2025-08-13T18:30:49Z)
• CAD-Judge: Toward Efficient Morphological Grading and Verification for Text-to-CAD Generation [7.802597811923231]
  CAD-Judge is a novel, verifiable reward system for efficient and effective CAD preference grading and grammatical validation.<n>We introduce a simple yet effective agentic CAD generation approach and adopt the Compiler-as-a-Review Module.
  arXiv  Detail & Related papers  (2025-08-06T01:30:56Z)
• CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning [31.342222156939403]
  We introduce CReFT-CAD, a two-stage fine-tuning paradigm that first employs a curriculum-driven reinforcement learning stage with difficulty-aware rewards to build reasoning ability steadily.<n>We release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning.
  arXiv  Detail & Related papers  (2025-05-31T13:52:56Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning [70.70393006697383]
  We present AutoCAD, a fully automatic and task-agnostic CAD generation framework. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework.
  arXiv  Detail & Related papers  (2022-11-29T13:39:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.