MCP-enabled LLM for meta-optics inverse design: leveraging differentiable solver without LLM expertise.
Gespeichert in:
| Titel: | MCP-enabled LLM for meta-optics inverse design: leveraging differentiable solver without LLM expertise. |
|---|---|
| Autoren: | Huang, Yi, Zheng, Bowen, Dong, Yunxi, Tang, Hong, Zhao, Huan, Shawon, Rakibul Hasan, An, Sensong, Zhang, Hualiang |
| Quelle: | Nanophotonics (21928606); Dec2025, Vol. 14 Issue 27, p5589-5602, 14p |
| Schlagwörter: | LANGUAGE models, AUTOMATIC differentiation, SOFTWARE frameworks, METAMATERIALS, REVERSE engineering, COMPUTER programming |
| Abstract: | Automatic differentiation (AD) enables powerful metasurface inverse design but requires extensive theoretical and programming expertise. We present a Model Context Protocol (MCP) assisted framework that allows researchers to conduct inverse design with differentiable solvers through large language models (LLMs). Since LLMs inherently lack knowledge of specialized solvers, our proposed solution provides dynamic access to verified code templates and comprehensive documentation through dedicated servers. The LLM autonomously accesses these resources to generate complete inverse design codes without prescribed coordination rules. Evaluation on the Huygens meta-atom design task with the differentiable TorchRDIT solver shows that while both natural language and structured prompting strategies achieve high success rates, structured prompting significantly outperforms in design quality, workflow efficiency, computational cost, and error reduction. The minimalist server design, using only 5 APIs, demonstrates how MCP makes sophisticated computational tools accessible to researchers without programming expertise, offering a generalizable integration solution for other scientific tasks. [ABSTRACT FROM AUTHOR] |
| Copyright of Nanophotonics (21928606) is the property of De Gruyter and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Datenbank: | Complementary Index |
Full Text 
Full Text Finder 
Nájsť tento článok vo Web of Science Schreiben Sie den ersten Kommentar!