Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Berger, Elias, Usama, Muhammad, Mehlstäubl, Jan, Saske, Bernhard, Paetzold-Byhain, Kristin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910236402515968
author Berger, Elias
Usama, Muhammad
Mehlstäubl, Jan
Saske, Bernhard
Paetzold-Byhain, Kristin
author_facet Berger, Elias
Usama, Muhammad
Mehlstäubl, Jan
Saske, Bernhard
Paetzold-Byhain, Kristin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19717
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
Berger, Elias
Usama, Muhammad
Mehlstäubl, Jan
Saske, Bernhard
Paetzold-Byhain, Kristin
Computer Vision and Pattern Recognition
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.
title Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.19717