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

Zhenyuan Zhao; Yu Xing; Tianyang Xue; Lingxin Cao; Xin Yan; Lin Lu

cs.AIMar 28, 2026

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

Authors: Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao, Xin Yan, Lin Lu

Organizations: Shandong University, Qingdao, China · The University of Hong Kong, Hong Kong, China

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.

Figures & tables

Figure 1: The AutoMS workflow: From abstract intent to concrete microstructure design. The system takes ambiguous semantic specifications as input and operationalizes them into quantifiable targets. Through a simulation-aware evolutionary loop, AutoMS iteratively refines the design candidates, resulting in optimized, topologically coherent microstructures that satisfy the initial cross-physics demands.

Figure 2: The AutoMS Multi-Agent Architecture for Cross-Physics Inverse Design. The framework comprises two hierarchical layers: Orchestration Layer: Governed by a Manager Agent, this layer coordinates the Parser (leveraging GraphRAG) to operationalize semantic intent into parametric targets, while the Generator, Simulator, and Reporter agents handle geometry synthesis, physical validation, and results synthesis, respectively. Optimization Layer: Functioning as the numerical engine, it executes Simulation-Aware Evolutionary Search (SAES) through four mathematical phases: Local Gradient Approximation (Perception) via Weighted Least Squares, Parameter Update (Action) using gradient-guided navigation, and Pareto-Driven Selection combined with Adaptive Weight Updates (Integration) to resolve conflicting objectives and break local optima.

Method	Completion		Solution Quality			Efficiency
Method	SR $\uparrow$	CSR $\uparrow$	MRE $\downarrow$	BPM $\uparrow$	QS $\uparrow$	Iter $\downarrow$	Time (s) $\downarrow$
NSGA-II	43.7%	53.3%	0.4276	51.7%	49.8	48.8	5550.2
ReAct	53.3%	53.6%	0.0345	67.2%	61.2	10.0	2843.9
BayesOpt	65.0%	55.6%	0.0194	85.6%	73.7	39.2	3982.9
CMA-ES	66.7%	55.7%	0.0241	84.7%	73.7	40.8	4202.3
S-SAES	69.2%	66.4%	0.0172	86.5%	78.2	9.6	1743.0

Table 1: Quantitative Benchmark Results. Comprehensive comparison of AutoMS against numerical and agentic baselines in a unified table. The framework is evaluated across three critical dimensions: Task Completion, Solution Quality and Efficiency.

Task	Property	Target	ReAct		NSGA-II		AutoMS
Task	Property	Target	Val	Err%	Val	Err%	Val	Err%
Task 1	$\kappa\>(\mathrm{W/(m\cdot K)})$	0.035	0.0220	-37.1	0.0554	+58.3	0.0340	-2.9
	$E\>(\mathrm{MPa})$	110	125.8	+14.4	484.7	+340.6	107.4	-2.4
	$\nu$	0.26	0.2652	+2.0	0.2960	+13.8	0.2558	-1.6
	$v_{f}\>(\%)$	30.0	29.03	-3.2	52.74	+75.8	28.24	-5.9
Task 2	$\sigma\>(\mathrm{S/m})$	3.8M	2.89M	-23.8	3.53M	-7.1	3.78M	-0.5

Table 2: Cross-Physics Fidelity Analysis on Representative Tasks. Quantitative validation on Task 1 (Two-Physics Precise) and Task 2 (Cross-Physics Precise). Err is defined in Appendix E.2 .

Figure 3: Visual Validation of Quantitative Benchmarks. A structural and functional comparison of the designs quantified in Table 2 .

Component ablations
Method	Completion		Solution Quality			Efficiency
Method	SR $\uparrow$	CSR $\uparrow$	MRE $\downarrow$	BPM $\uparrow$	QS $\uparrow$	Iter $\downarrow$	Time (s) $\downarrow$
AutoMS (Full)	83.8%	59.6%	0.0140	94.2%	82.4	14.4	2180.5
w/o Local Grad.	66.7%	38.7%	0.0207	84.4%	68.5	14.6	1787.4
w/o Adapt. Weight	71.7%	26.8%	0.0261	86.1%	66.5	15.7	1965.9
w/o SAES	78.3%	76.2%	0.0302	89.7%	80.4	16.8	2885.9

Table 3: Ablation study results. Results are organized into component ablations and reasoning and algorithmic engine variants.

Figure 4: Visualization of Optimization Trajectories. The scatter plots illustrate the evolutionary search process in the cross-physics property space ( $E$ vs. $\kappa$ ). Candidates are color-coded by generation index to visualize temporal progression. The blue arrows trace the optimization path, highlighting the contrast between the directed convergence of AutoMS (Left) and the erratic, divergent search pattern of the baseline without SAES (Right).

LLM Core	Completion		Solution Quality			Efficiency
LLM Core	SR $\uparrow$	CSR $\uparrow$	MRE $\downarrow$	BPM $\uparrow$	QS $\uparrow$	Iter $\downarrow$	Time (s) $\downarrow$
GPT-4o	71.8%	59.8%	0.0439	84.6%	75.5	13.4	1022.7
GPT-5.2	84.6 %	52.0%	0.0188	87.2%	76.2	12.3	2379.2
Claude Haiku 4.5	76.9%	64.7%	0.0397	89.7%	80.1	10.7	1142.0
Qwen3-Max	82.3%	68.8%	0.0247	92.6%	81.5	14.9	1845.8
DeepSeek-V3.2	83.8%	59.6%	0.0140	94.2%	82.4	14.4	2180.5

Table 4: Robustness Analysis across LLM Logic Cores. Performance comparison of AutoMS across diverse LLM cores, showing that robustness is mainly driven by the AutoMS architecture rather than any single model.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Module	Parameter	Value
Optimization	Population Size ( $N_{pop}$ )	20
	Elite Archive Size	50
	Max Iterations	10
Perception	Neighbor Window ( $M$ )	5
(Local Gradient)	Temporal Decay ( $\lambda_{t}$ )	0.5
	Outlier Threshold	2.5 MAD

Appendix

Table 5: SAES Hyperparameters

ID	Difficulty	Task Name	Target Objectives	MRE $\downarrow$	BPM $\uparrow$	CSR $\uparrow$	QS $\uparrow$	Iter $\downarrow$	Time(s) $\downarrow$
1	Hard	Two-Physics Precise	$\kappa=0.035,E=110\>\mathrm{MPa},\nu=0.26,v_{f}=30\%$	0.0320	65.00%	14.20%	44.90	13.0	2689.2
2	Hard	Cross-Physics Precise	$\sigma=3.8\times 10^{6}\>\mathrm{S/m},\kappa=26,E=3\>\mathrm{GPa},\nu=0.25,v_{f}=25\%$	0.0174	80.00%	21.40%	53.09	12.9	2034.1
3	Easy	High Electrical Cond.	Max $\sigma$ ( $>3.5\times 10^{6}\>\mathrm{S/m}$ )	0.0010	100.00%	38.40%	81.51	11.2	1535.4
4	Medium	Thermal-Stiffness	$\kappa\approx 26,E\approx 3.8\>\mathrm{GPa}$	0.0253	100.00%	62.60%	88.53	17.0	2975.9
5	Medium	Tri-Field Coupling	$\kappa\approx 25,\sigma\approx 3\times 10^{6}\>\mathrm{S/m},E\approx 3\>\mathrm{GPa}$	0.0195	100.00%	67.50%	90.06	18.8	2693.3
6	Medium	Pareto Thermal-Mass	Max $\kappa$ , Min $v_{f}$	0.0072	100.00%	78.70%	93.54	15.5	2153.8

Appendix

Table 6: Quantitative performance analysis of the 17-task AutoMS Benchmark. The tasks are stratified by difficulty based on the cardinality of physical constraints and simulation complexity (e.g., non-linear plasticity). Crucially, AutoMS maintains a low Mean Relative Error (MRE) across all regimes, particularly in ”Hard” tasks. This demonstrates that the framework does not merely locate feasible regions but converges to high-fidelity designs that precisely match rigorous cross-physics targets.

Figure 5: Gallery of Optimized Microstructures. A visualization of the best-performing unit cell for each of the 17 benchmark tasks. The diversity of the generated topologies highlights AutoMS’s ability to discover physics-aware geometries

Figure 6: Gallery of 3D-printed microstructures. These representative samples showcase the topological diversity and robust manufacturability of the optimal designs discovered by AutoMS across the 17-task benchmark.

Task	Difficulty	SR	CSR	MRE	BPM	QS
T1	Hard	0%	0%	0.6099	33%	17.2
T2	Hard	0%	0%	0.6067	25%	13.9
T3	Easy	100%	100%	0.0010	100%	100.0
T4	Medium	0%	0%	0.0375	33%	23.0
T5	Medium	0%	80%	0.0452	75%	63.5
T6	Medium	100%	100%	0.0048	100%	100.0

Appendix

Table 7: One-shot MIND baseline on the 17-task suite. This baseline performs single-pass generation without iterative SAES correction.

Metric	Mean	Standard Deviation
SR	83.8%	3.3%
CSR	59.6%	13.1%
MRE	0.0140	0.0072
BPM	94.2%	1.7%
QS	82.4	4.67
Iter	14.4	8.05

Appendix

Table 8: Statistical robustness over four independent runs. Mean and standard deviation are reported on the 17-task benchmark.

Generator	SR $\uparrow$	CSR $\uparrow$	MRE $\downarrow$	BPM $\uparrow$	QS $\uparrow$	Iter $\downarrow$	Time (s) $\downarrow$
MIND ( Xue et al., 2025 )	83.8%	59.6%	0.0140	94.2%	82.4	14.4	2180.5
Yang et al. ( Yang et al., 2026 )	73.3%	57.7%	0.0137	88.9%	80.7	12.3	4223.3

Appendix

Table 9: Generator dependence analysis. MIND is replaced by the weaker generator from Yang et al. ( Yang et al., 2026 ) while keeping the AutoMS framework unchanged.

Metric	Value
Total wall-clock time	2180.5 s
LLM inference time	669.4 s (30.7%)
Simulation / tool execution time	1508.9 s (69.2%)
Average token usage	457,306
Input tokens	436,911
Output tokens	20,395

Appendix

Table 10: Compute and token breakdown per task. Statistics are averaged over four runs on the 17-task benchmark.

Explore similar work

OptiMAS: Automatically Optimize Multi-Agent System
Aug 22, 2026Yuxin Cheng, Chang Liu, Hanxin Yu +9Multi-Agent System Optimization Multi-Agent LLM Systems
The University of Hong Kong · Huawei Foundation Model Department, Huawei Technologies Ltd. · City University of Hong Kong +2
Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
May 22, 2026Hyunjee Park, Hayoung ChungTopology Optimization Multi-Agent LLM Systems
Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of Korea
AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment
Mar 4, 2026Jiangyu ChenLarge Language Model-Guided Scientific Discovery Neuro-Symbolic AI
State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University · Suzhou Laboratory

Aug 22, 2026J/K move · Enter open · S save

OptiMAS: Automatically Optimize Multi-Agent System

Yuxin Cheng, Chang Liu, Hanxin Yu, Haochen Tan+8

The University of Hong Kong · Huawei Foundation Model Department, Huawei Technologies Ltd. · City University of Hong Kong+2

Multi-Agent System Optimization Multi-Agent LLM Systems Self-Evolving Agents

Open paper AskPDF arXiv

Automated evolution of Multi-Agent Systems (MAS) holds significant potential for reducing the manual effort required to design and optimize LLM-based agent architectures. However, extant search-based paradigms face a fundamental trade-off, where an expanded optimization scope exacerbates evolutionary instability, while discrete branch-and-discard search isolates insights across lineages. To address these limitations, we propose a continuous, data-driven optimization paradigm built upon a unified ReAct-based infrastructure that reconciles a broad optimization scope with operational stability. Under this paradigm, we present OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution. Equipped with a novel dual-track memory mechanism, OptiMAS sustains performance improvement over extended optimization horizons. Evaluation on four heterogeneous agentic benchmarks with three varying scale and accessibility LLM backbones, demonstrates that OptiMAS consistently achieves competitive or superior accuracy relative to both domain-specialized hand-crafted systems and existing evolutionary methods. Our work establishes a practical milestone toward robust, automated MAS evolution.

Abstract

Explore similar work

OptiMAS: Automatically Optimize Multi-Agent System

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework

AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment