2026 Liu Embodied CAD Parametric BRep Assembly

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, a closed-loop framework that grounds an LLM agent in a CAD execution environment. 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 operation-family prediction, 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, task completion, and FreeCAD execution 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.