Toward a Universal Meta-Optics Solver via Large Language Models

Abstract

Metasurface design increasingly requires fast models that can operate across structurally distinct device families rather than retraining a separate surrogate for every geometry class. Conventional neural network surrogates often depend on fixed-dimensional descriptors, family-specific output formats, and repeated architecture tuning, which limit their scalability across heterogeneous meta-atoms. Here, we present a unified large language model (LLM) workflow for multifamily metasurface modeling and inverse design. Geometries, design parameters, and optical response channels were converted into a shared instruction-following text format and used to fine-tune Gemma-2-9B across 8 metasurface families. Compared with single-family baselines, the joint model simultaneously predicted the optical responses of all metasurface families while reducing the MSE for each family by an average of 56.5%. The same representation was also used for the inverse design. These results show that a shared sequence-based LLM interface can provide a practical route to cross-family metasurface design while reducing the need for task-specific surrogate architectures.