Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling
For industrial CAD modeling, this work addresses the challenge of generating geometrically valid and editable assembly scripts, but the results are incremental, showing high executable rates but limited exact policy accuracy.
Embodied CAD introduces solver-grounded LLM agents that iteratively construct parametric B-Rep assemblies using a stratified skill library and solver feedback, achieving high executable rates and exposing gaps in long-horizon policy prediction on multi-step mechanical assembly tasks.
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.