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

TL;DR

AutoMS introduces a multi-agent neuro-symbolic framework using LLMs and evolutionary search to efficiently solve complex cross-physics inverse microstructure design problems, outperforming traditional methods.

Contribution

It presents a novel combination of LLM-driven semantic decomposition with simulation-aware evolutionary search for inverse design tasks.

Findings

Achieved 83.8% success rate on 17 diverse cross-physics tasks.

Significantly outperforms traditional evolutionary algorithms.

Decouples semantic orchestration from numerical optimization for robustness.

Abstract

Designing microstructures with coupled cross-physics objectives is a fundamental challenge where traditional topology optimization is often computationally prohibitive and deep generative models frequently suffer from physical hallucinations. We introduce AutoMS, a multi-agent neuro-symbolic framework that reformulates inverse design as an LLM-driven evolutionary search. AutoMS leverages LLMs as semantic navigators to decompose complex requirements and coordinate agent workflows, while a novel Simulation-Aware Evolutionary Search (SAES) mechanism handles low-level numerical optimization via local gradient approximation and directed parameter updates. This architecture achieves a state-of-the-art 83.8% success rate on 17 diverse cross-physics tasks, significantly outperforming both traditional evolutionary algorithms and existing agentic baselines. By decoupling open-ended semantic orchestration from simulation-grounded numerical search, AutoMS provides a robust pathway for navigating complex physical landscapes that remain intractable for standard generative or purely linguistic approaches.