{"type":"ScholarlyArticle","title":"Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design","authors":[{"name":"Elias Berger","slug":"elias-berger","given":"Elias","family":"Berger","affiliation":""},{"name":"Muhammad Usama","slug":"muhammad-usama","given":"Muhammad","family":"Usama","affiliation":""},{"name":"Jan Mehlstäubl","slug":"jan-mehlstaubl","given":"Jan","family":"Mehlstäubl","affiliation":""},{"name":"Bernhard Saske","slug":"bernhard-saske","given":"Bernhard","family":"Saske","affiliation":""},{"name":"Kristin Paetzold-Byhain","slug":"kristin-paetzold-byhain","given":"Kristin","family":"Paetzold-Byhain","affiliation":""}],"abstract":"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 4.2x 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.","doi":"10.24963/ijcai.2026/714","url":"https://ijcai.org/proceedings/2026/714","pdf":"https://ijcai.org/proceedings/2026/0714.pdf","markdown":"https://ijcai.org/proceedings/2026/714.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/714","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":714,"pages":{"first":6417,"last":6425},"keywords":["Advanced AI4Tech: Generative and LLMs-driven AI4Tech","Domain-specific AI4Tech: AI4Manufacturing","AI4T: Domain-specific AI4Tech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}