发表机构
The Pennsylvania State University; University of Tennessee at Chattanooga（宾夕法尼亚州立大学; 田纳西大学查塔努加分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该综述探讨大语言模型（LLMs）如何通过语义接口、代码生成及工具编排改进纳米光子学工作流，梳理相关方法的两类模式及跨学科应用，展望具备物理感知的多模态基础模型，推动AI从被动工具向主动科研合作者转变。
AI 中文摘要
超表面通过实现前所未有的光操纵精度，彻底改变了光子器件的发展。然而，其设计过程常受限于计算成本高昂的模拟和复杂的高维设计空间。尽管深度学习已作为代理模型加快了设计进程，但它仍受限于任务特定架构，缺乏通用推理能力。本综述探讨大语言模型（LLMs）如何为成熟的数值纳米光子学工作流增添语义接口、代码生成与工具编排功能。我们首先概述从经典神经网络到基于Transformer的模型的发展及其在纳米光子设计中的应用；接着综述纳米光子学中LLM相关方法的出现，并将其分为两种操作模式：将结构-光谱映射视为语言任务的代理模型，以及已被证实可生成代码、编排选定模拟步骤并支持闭环优化的智能体系统。此外，为明确未来跨学科机遇，我们简要探索了LLMs在材料科学、无线通信等研究领域的应用。本综述最后展望具备物理感知能力的下一代多模态基础模型，在该愿景中，人工智能正从被动工具演变为主动合作者，参与自主科学发现。
英文摘要
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.
CommentsAccepted for publication in Advanced Photonics
Journal refAdv. Photon. 8(5), 054003 (2026)
