Photonics-GCCE：面向通用与自主光学设计的群组协作-竞争演化多智能体框架

Physics > Optics arXiv:2609.28045 (physics) [Submitted on 23 Sep 2026] Title:Photonics-GCCE: group collaborative-competitive evolution multi-agent framework for universal and autonomous optical design Authors:Weijie Xu, Ming Wang, Ruicheng Ma, Zeyong Wei, Di Zhang, Jian Chen, Zining Wang, Sijun Hu, Linyuan Dou, Haoyu Li, Haigang Liang, Yijie Luo, Shuqiao Li, Qinghua Song, Huihui Zhu, Hongfei Jiao, Chao Liu, Ali Momeni, Zhanshan Wang, Yuzhi Shi, Romain Fleury, Cheng-Wei Qiu, Xinbin Cheng View a PDF of the paper titled Photonics-GCCE: group collaborative-competitive evolution multi-agent framework for universal and autonomous optical design, by Weijie Xu and 21 other authors View PDF Abstract: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. Comments: Subjects: Optics (physics.optics) Cite as: arXiv:2609.28045 [physics.optics] (or arXiv:2609.28045v1 [physics.optics] for this version) https://doi.org/10.48550/arXiv.2609.28045 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Yuzhi Shi Prof. [view email] [v1] Wed, 23 Sep 2026 13:04:29 UTC (6,268 KB) Full-text links: Access Paper: View a PDF of the paper titled Photonics-GCCE: group collaborative-competitive evolution multi-agent framework for universal and autonomous optical design, by Weijie Xu and 21 other authors View PDF view license Current browse context: physics.optics new | recent | 2026-09 Change to browse by: physics References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)