Story
arxiv_cs_cl ยท Sep 3, 2026 ยท paper
arxiv.orgSep 3, 2026
original source linked
In brief
Parametric computer-aided design (CAD) modeling is difficult to evaluate with a single metric. Existing CAD benchmarks often emphasize synthetic or CAD-native settings, limited input modalities, or executability and I...
Feed lens
agentevaluationcodex