Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
For engineers and AI researchers, this work addresses the lack of physical validation in LLM-generated CAD designs by integrating explicit physical verification into the design loop.
The paper introduces a hybrid agentic-physical architecture for CAD engineering design that embeds validated knowledge-based tools into LLM-driven decision making, achieving a 4.2× increase in structural complexity and 3.5% improvement in compile rate over similar agentic methods.
Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly learn physical laws from data, we propose a Hybrid Agentic-Physical Architecture that embeds validated knowledge-based engineering tools directly into the decision making loop of autonomous AI agents. In this framework, engineering design is formulated as a closed-loop, sequential decision making process guided by explicit physical verification. Based on a load case, dedicated agents iteratively plan, generate, evaluate, and revise engineering designs using knowledge-based tools as a feedback signal. We introduce a benchmark dataset and metrics for assessing functional validity in generative CAD. Our system generates more complex and physically verified designs, with a 4.2 increase in structural complexity and improving compile rate by 3.5% compared to similar agentic methods. The codebase, prompts and dataset will be made publicly available to support reproducibility and future research.