发表机构
Institute of Precision Optical Engineering, School of Physics Science and Engineering, Tongji University; MOE Key Laboratory of Advanced Micro-Structured Materials; Shanghai Frontiers Science Center of Digital Optics; Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications; Tsinghua Shenzhen International Graduate School, Tsinghua University; College of Information Science and Electronic Engineering and ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University; Department of Electronic Engineering, Tsinghua University; Laboratory of Wave Engineering, Department of Electrical Engineering, EPFL; Department of Electrical and Computer Engineering, National University of Singapore（同济大学物理科学与工程学院精密光学工程研究所; 教育部先进微结构材料重点实验室; 上海数字光学前沿科学中心; 上海市全谱高性能光学薄膜器件及应用专业技术服务平台; 清华大学深圳国际研究生院; 浙江大学信息与电子工程学院及浙大杭州全球科创中心; 清华大学电子工程系; 瑞士联邦理工学院电气工程系波工程实验室; 新加坡国立大学电气与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Photonics-GCCE多智能体框架，通过群体协作与竞争进化实现自主光学设计，提升综合得分至90多分，制造鲁棒性提高15-17分，迭代约40轮，并实现质量因子13120的准BIC器件。
AI 中文摘要
基于大语言模型（LLM）的光子智能体将自然语言意图与可执行求解器相连接，相比传统光学设计方法展现出显著优势。然而，当前的多智能体框架在协作范式下运行，缺乏外部选择压力，可能继承共同的盲点、过早收敛，并且无法为复杂任务积累可迁移的经验。在此，我们提出一种群体光子协作-竞争进化（GCCE）框架及其LLM实例化，称为Photonics-GCCE。两个独立的智能体群体追求相同的设计目标，并在折射率保真度、制造敏感性、算法充分性和物理一致性方面经历结构化的竞争性评估。每个群体由一名领导者和三名分别负责材料、优化和代码验证的专家智能体组成。智能体通过跨设计轮次的竞争性评估来完善其技能。在六个器件类别上，与单智能体和多智能体基线进行基准测试表明，Photonics-GCCE将综合得分提升至90多分，将制造鲁棒性提高15至17分，并将求解器迭代次数减少至约40轮。一个代表性的准BIC演示实现了质量因子为13120的实际可制造设计。我们的结果表明，Photonics-GCCE是一个用于自主光学设计的通用闭环框架，能够在多样化的纳米光子学任务中产生高性能、可制造就绪的器件。
英文摘要
Large language model (LLM)-empowered photonic agents connect natural-language intents to executable solvers, showing significant advantages over conventional optical design approaches. However, current multi-agent frameworks operate within a collaborative paradigm without extrinsic selective pressure, which could inherit shared blind spots, converge prematurely, and fail to accumulate transferable experience for intricate tasks. Here, we introduce a group photonics collaboration-compete evolution (GCCE) framework and its LLM instantiation, termed Photonics-GCCE. Two independent agent groups pursue the same design target and undergo structured competitive evaluation across refractive-index fidelity, fabrication sensitivity, algorithmic adequacy, and physical consistency. Each group comprises a leader and three specialist agents dedicated to materials, optimization, and code validation. Agents refine their skills through competitive evaluation across design rounds. Benchmarking across six device categories against single-agent and multi-agent baselines shows that Photonics-GCCE elevates composite scores into the high 90s, improves fabrication robustness by 15 to 17 points, and reduces solver iterations to roughly 40 rounds. A representative quasi?BIC demonstration achieves a practically fabricable design with a quality factor of 13120. Our results demonstrate Photonics-GCCE as a general-purpose and closed-loop framework for autonomous optical design, capable of producing high-performance, fabrication-ready devices across diverse nanophotonic tasks.
Comments35 pages, 5 figures
