An Agent-Driven, Cross-Validated Inverse-Design Pipeline for Dielectric Metasurfaces
Abstract
Inverse design of dielectric metasurfaces is powerful but labour-intensive: each new target requires choosing a parameterization and a figure of merit, managing compute resources, and critically assessing results that may be numerically unconverged, sensitive to fabrication errors or trapped in local optima. Here we present an open-source pipeline in which an artificial intelligence (AI) coding agent turns a plain-language specification into metasurface optimization runs, executes them, analyses every run with a fixed checklist and proposes the next iteration. Designs are optimized with differentiable three-dimensional rigorous coupled-wave analysis (RCWA), including robustness to fabrication tolerances, and every reported design is independently verified with finite-difference time-domain (FDTD) simulations. We demonstrate the workflow at 1550 nm on a freeform silicon metagrating, on a polarization-independent meta-atom library assembled into beam-deflecting supercells, and on metalenses built from the same library. In the metagrating case, the independent FDTD verification revealed a 5\% overestimate of the efficiency by the optimization model that a conventional convergence test had not detected, and the robust design retained most of its efficiency under ±10~nm fabrication errors. In the other cases, instead, the obtained RCWA results are confirmed by full-wave simulations.
Related
- Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments
- Spin-to-orbital angular momentum conversion in dielectric metasurfaces
- Spin-to-orbital angular momentum conversion in dielectric metasurfaces: erratum
- Novel functionalities enabled by asymmetric reconfiguration in VO2-dielectric metasurfaces
- Reconfigurable Generation of Terahertz Spiral Vector Beams Based on All-Dielectric Cascaded Metasurfaces
BibTeX
@misc{lio2026agentdriven,
title = {{An Agent-Driven, Cross-Validated Inverse-Design Pipeline for Dielectric Metasurfaces}},
author = {Giuseppe Emanuele Lio and Roberto Caputo and Alain J. Corso and Maria Guglielmina Pelizzo and Antonio Ferraro},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08127},
eprint = {2611.08127},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08127},
}
RIS
TY - UNPB
TI - An Agent-Driven, Cross-Validated Inverse-Design Pipeline for Dielectric Metasurfaces
AU - Giuseppe Emanuele Lio
AU - Roberto Caputo
AU - Alain J. Corso
AU - Maria Guglielmina Pelizzo
AU - Antonio Ferraro
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.08127
UR - https://arxiv.org/abs/2611.08127
AB - Inverse design of dielectric metasurfaces is powerful but labour-intensive: each new target requires choosing a parameterization and a figure of merit, managing compute resources, and critically assessing results that may be numerically unconverged, sensitive to fabrication errors or trapped in local optima. Here we present an open-source pipeline in which an artificial intelligence (AI) coding agent turns a plain-language specification into metasurface optimization runs, executes them, analyses every run with a fixed checklist and proposes the next iteration. Designs are optimized with differentiable three-dimensional rigorous coupled-wave analysis (RCWA), including robustness to fabrication tolerances, and every reported design is independently verified with finite-difference time-domain (FDTD) simulations. We demonstrate the workflow at 1550 nm on a freeform silicon metagrating, on a polarization-independent meta-atom library assembled into beam-deflecting supercells, and on metalenses built from the same library. In the metagrating case, the independent FDTD verification revealed a 5\% overestimate of the efficiency by the optimization model that a conventional convergence test had not detected, and the robust design retained most of its efficiency under ±10~nm fabrication errors. In the other cases, instead, the obtained RCWA results are confirmed by full-wave simulations.
ER -