{"ID":5438690,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T07:17:43.555462792Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31252","arxiv_id":"2606.31252","title":"Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling","abstract":"Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires more than syntactically valid code: every feature, placement, and assembly relation must be accepted by an exact geometric kernel while remaining editable as parametric boundary representation geometry. We present Embodied CAD, solver-grounded LLM agents for parametric B-Rep assembly modeling. Instead of generating a complete script in one pass, the agent iteratively selects actions from a stratified L0-L4 CAD skill library, resolves them into typed geometric operations, executes them in a CAD backend, and uses solver feedback to plan, repair, and learn. The framework combines action grammar constraints, deterministic parameter resolution, and solver-derived rewards for supervised warm-up and GRPO-style refinement. We evaluate Embodied CAD on multi-step mechanical, industrial equipment, and mold-oriented assembly tasks using solver-aligned metrics: executable rate, skill accuracy, operation-family accuracy, exact policy accuracy, and task completion success. The results show that solver-grounded planning executes all strong-planner workflows in the current benchmark, while learned controllers reach high executable rates and expose the remaining gap between valid tool calls and exact long-horizon policy prediction.","short_abstract":"Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires more than syntactically valid code: every feature, placement, and assembly relation must be accepted by an exact geometric kernel while remaining editable as parametric boundary representation geometry. We present Embod...","url_abs":"https://arxiv.org/abs/2606.31252","url_pdf":"https://arxiv.org/pdf/2606.31252v1","authors":"[\"Fumin Liu\",\"Haoyu Zhou\",\"Fei Hao\",\"Lin Yang\"]","published":"2026-06-30T07:31:01Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}