A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design
Abstract
Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal reasoning capabilities. This review surveys how Large Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of multimodal foundation models with physical perception capabilities. In this vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.
Versions
Related
- Mechanism-informed dynamic surrogate modeling for rapid thermal-aberration prediction in bonded optical systems
- Physics-constrained neural networks for surrogate modeling of lossless periodic structures
- Machine learning surrogate modeling with quantile adjustment for landing gear surface pressure fluctuation prediction
- A hierarchy of physics-embedded neural operators for structural dynamic surrogate modelingA hierarchy of physics-embedded neural operators for structural dynamic surrogate modeling
- A Pre-trained Variational Autoencoder for Gyrokinetic Plasma Turbulence Surrogate Modeling
BibTeX
@misc{zhang2026comprehensive,
title = {{A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design}},
author = {Huanshu Zhang and Kegeng Tang and Lei Kang and Sawyer D. Campbell and Zihao Wang and Douglas H. Werner},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.18279},
eprint = {2608.18279},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.18279},
}
RIS
TY - UNPB
TI - A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design
AU - Huanshu Zhang
AU - Kegeng Tang
AU - Lei Kang
AU - Sawyer D. Campbell
AU - Zihao Wang
AU - Douglas H. Werner
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2608.18279
UR - https://arxiv.org/abs/2608.18279
AB - Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal reasoning capabilities. This review surveys how Large Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of multimodal foundation models with physical perception capabilities. In this vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.
ER -