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

arXiv: https://arxiv.org/abs/2603.27195 · HTML: https://mlsanity.com/paper/2603.27195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 29 of 29)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators](https://mlsanity.com/paper/1910.03193/) (2019)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [Diffusion Models Beat GANs on Topology Optimization](https://mlsanity.com/paper/2208.09591/) (2022)
- [Inverse-design of nonlinear mechanical metamaterials via video denoising diffusion models](https://mlsanity.com/paper/2305.19836/) (2023)
- [JAX-FEM: A differentiable GPU-accelerated 3D finite element solver for automatic inverse design and mechanistic data science](https://mlsanity.com/paper/2212.00964/) (2022)
- [MetaOpenFOAM: an LLM-based multi-agent framework for CFD](https://mlsanity.com/paper/2407.21320/) (2024)
- [Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties](https://mlsanity.com/paper/2302.12881/) (2023)
- [MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines](https://mlsanity.com/paper/2507.22606/) (2025)
- [PINNsAgent: Automated PDE Surrogation with Large Language Models](https://mlsanity.com/paper/2501.12053/) (2025)
- [MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation](https://mlsanity.com/paper/2504.08621/) (2025)
- [LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins](https://mlsanity.com/paper/2405.18092/) (2024)
- [Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models](https://mlsanity.com/paper/2502.11075/) (2025)
- [Microstructure synthesis using style-based generative adversarial network](https://mlsanity.com/paper/1909.07042/) (2019)
- [A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools](https://mlsanity.com/paper/2506.20743/) (2025)
- [Physics simulation capabilities of LLMs](https://mlsanity.com/paper/2312.02091/) (2023)
- [MIND: Microstructure INverse Design with Generative Hybrid Neural Representation](https://mlsanity.com/paper/2502.02607/) (2025)
- [ChemHTS: Hierarchical Tool Stacking for Enhancing Chemical Agents](https://mlsanity.com/paper/2502.14327/) (2025)
- [Material Microstructure Design Using VAE-Regression with Multimodal Prior](https://mlsanity.com/paper/2402.17806/) (2024)
- [MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation](https://mlsanity.com/paper/2508.17568/) (2025)
- [Inverse Design of Metamaterials with Manufacturing-Guiding Spectrum-to-Structure Conditional Diffusion Model](https://mlsanity.com/paper/2506.07083/) (2025)
- [PCG-Informed Neural Solvers for High-Resolution Homogenization of Periodic Microstructures](https://mlsanity.com/paper/2506.17087/) (2025)

## Built on by (most cited first, 1 of 1)

- [A property-registry contract for retrieve-or-refuse thermal-mechanical lattice search](https://mlsanity.com/paper/2609.14741/) (2026)

## Abstract (arXiv)

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.