Autonomous Generation of Metamaterial Databases Based on Multimodal Agents

Abstract

Artificial intelligence (AI) is revolutionizing material research and discovery. However, its development in metamaterials is bottlenecked by a shortage of high-quality and executable structure-response databases, which are locked within scientific literatures as a mixture of text and images. Converting the rapidly growing body of scientific literatures into executable and reusable databases for machine-driven discovery is still a fundamental challenge. Here, we propose MetaDataGenAgent, a multimodal multi-agent framework that autonomously converts unstructured scientific literatures directly into metamaterial structure-response databases. MetaDataGenAgent establishes a complete literature-to-simulation pipeline through the coordinated operation of specialized agents for multimodal parameter extraction, physics-guided validation, topology-aware structural analysis, and solver-executable encoding. The framework introduces a closed-loop plan-execute-reflect mechanism that enables dynamic task decomposition, iterative validation, and feedback-driven model construction. Experimental results validate that MetaDataGenAgent can generate high-fidelity structure-response data for representative meta-atoms, which are further used to realize diverse electromagnetic functions, including far-field beam deflection, near-field holographic imaging and topologically protected surface-wave transport. By establishing an autonomous route from scientific literatures to AI-ready databases, the framework provides a general and efficient strategy that could be extended to a broad range of data-scarce scientific domains, including photonics, materials science, chemistry, computational science, and scientific automation.