AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design

Computer Science > Artificial Intelligence [Submitted on 28 Mar 2026] AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao, Xin Yan, Lin Lu Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material science. This inverse design problem involves a vast, discontinuous search space where traditional topology optimization is computationally prohibitive, and deep generative models often suffer from "physical hallucinations," lacking the capability to ensure rigorous validity. To address this limitation, we introduce AutoMS, a multi-agent neuro-symbolic framework that reformulates inverse design as an LLM-driven evolutionary search. Unlike methods that treat LLMs merely as interfaces, AutoMS integrates them as "semantic navigators" to initialize search spaces and break local optima, while our novel Simulation-Aware Evolutionary Search (SAES) addresses the "blindness" of traditional evolutionary strategies. Specifically, SAES utilizes simulation feedback to perform local gradient approximation and directed parameter updates, effectively guiding the search toward physically valid Pareto frontiers. Orchestrating specialized agents (Manager, Parser, Generator, and Simulator), AutoMS achieves a state-of-the-art 83.8\% success rate on 17 diverse cross-physics tasks, nearly doubling the performance of traditional NSGA-II (43.7\%) and significantly outperforming ReAct-based LLM baselines (53.3\%). Furthermore, our hierarchical architecture reduces total execution time by 23.3\%. AutoMS demonstrates that autonomous agent systems can effectively navigate complex physical landscapes, bridging the gap between semantic design intent and rigorous physical validity. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.27195 [cs.AI]   (or arXiv:2603.27195v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.27195 Focus to learn more Submission history From: Yu Xing [view email] [v1] Sat, 28 Mar 2026 08:51:33 UTC (3,390 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)