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

2026-03-28

AI Summary

This work addresses the challenges in inverse microstructural design under multiphysics coupling constraints—namely, the high computational cost of conventional topology optimization and the tendency of deep generative models to produce physically invalid “hallucinations.” To overcome these issues, the authors propose a Simulation-Aware Evolutionary Search (SAES) framework that, for the first time, leverages a large language model as a semantic navigator to orchestrate multi-agent co-evolution. This approach unifies semantic intent with physical feasibility by employing semantic guidance for population initialization and escape from local optima, while incorporating simulation feedback to approximate gradients and update parameters. Evaluated across 17 multiphysics tasks, SAES achieves an 83.8% success rate—substantially outperforming NSGA-II (43.7%) and ReAct (53.3%)—and reduces total execution time by 23.3%.

Abstract

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.

Problem

• inverse design
• microstructure
• cross-physics
• multi-objective optimization
• physical validity

Innovation

• multi-agent system
• neuro-symbolic AI
• inverse design
• evolutionary search
• cross-physics optimization