CADReasoner: Iterative Program Editing for CAD Reverse Engineering
This addresses the challenge of producing high-quality CAD parts with fine geometric details, which is incremental as it builds on existing AI systems by mimicking human iterative refinement.
The paper tackles the problem of CAD reverse engineering by introducing CADReasoner, a model that iteratively refines predictions using geometric discrepancies, achieving state-of-the-art results on benchmarks like DeepCAD, Fusion 360, and MCB.
Computer-Aided Design (CAD) powers modern engineering, yet producing high-quality parts still demands substantial expert effort. Many AI systems tackle CAD reverse engineering, but most are single-pass and miss fine geometric details. In contrast, human engineers compare the input shape with the reconstruction and iteratively modify the design based on remaining discrepancies. Agent-based methods mimic this loop with frozen VLMs, but weak 3D grounding of current foundation models limits reliability and efficiency. We introduce CADReasoner, a model trained to iteratively refine its prediction using geometric discrepancy between the input and the predicted shape. The model outputs a runnable CadQuery Python program whose rendered mesh is fed back at the next step. CADReasoner fuses multi-view renders and point clouds as complementary modalities. To bridge the realism gap, we propose a scan-simulation protocol applied during both training and evaluation. Across DeepCAD, Fusion 360, and MCB benchmarks, CADReasoner attains state-of-the-art results on clean and scan-sim tracks.