Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization
Abstract
Topology optimization has become an indispensable design tool in the aerospace, automotive, and mechanical engineering industries. Yet bringing a new problem from its description to an optimized result remains slow, expert-dependent, and unreliable: the workflow spans many manually connected stages, each new problem requires solver code to be written and debugged manually, and such code often fails or yields incorrect results. We present Agent4FreeFem, a pipeline driven by a large language model that turns a natural-language problem description into a set of verified optimization results without manual solver-code development or debugging. The pipeline keeps the problem definition unmodified, localizes errors using independent sources of evidence, and completes constrained repairs automatically, thereby providing efficient end-to-end automation, autonomous execution, and verifiable results. We evaluated Agent4FreeFem on a suite of single-physics and coupled multiphysics problems. Every case passed runtime verification and finished within the repair budget of each stage.
Related
- Robustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier
- SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification
- A new algorithm for topology optimization using a level-set method
- Topology Optimization for Generating Optimal Free-Form Rotor Structures in PMSMs
- ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization
BibTeX
@misc{cui2026agent4freefem,
title = {{Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization}},
author = {Zhipu Cui and Helin Gong and Shengfeng Zhu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00803},
eprint = {2611.00803},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00803},
}
RIS
TY - UNPB
TI - Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization
AU - Zhipu Cui
AU - Helin Gong
AU - Shengfeng Zhu
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00803
UR - https://arxiv.org/abs/2611.00803
AB - Topology optimization has become an indispensable design tool in the aerospace, automotive, and mechanical engineering industries. Yet bringing a new problem from its description to an optimized result remains slow, expert-dependent, and unreliable: the workflow spans many manually connected stages, each new problem requires solver code to be written and debugged manually, and such code often fails or yields incorrect results. We present Agent4FreeFem, a pipeline driven by a large language model that turns a natural-language problem description into a set of verified optimization results without manual solver-code development or debugging. The pipeline keeps the problem definition unmodified, localizes errors using independent sources of evidence, and completes constrained repairs automatically, thereby providing efficient end-to-end automation, autonomous execution, and verifiable results. We evaluated Agent4FreeFem on a suite of single-physics and coupled multiphysics problems. Every case passed runtime verification and finished within the repair budget of each stage.
ER -