A multi-agentic framework for real-time, autonomous freeform metasurface design.

Lupoiu, Robert; Shao, Yixuan; Dai, Tianxiang; Mao, Chenkai; Edée, Kofi; Fan, Jonathan A · Sci Adv · 2025

basic_science · Level V

Where this comes from

Abstract

Innovation in nanophotonics currently relies on human experts who synergize specialized knowledge in photonics and coding with simulation and optimization algorithms, entailing design cycles that are time-consuming, computationally demanding, and frequently suboptimal. We introduce MetaChat, a multi-agentic design framework that can translate semantically described photonic design goals into high-performance, freeform device layouts in an automated, nearly real-time manner. Multistep reasoning is enabled by our Agentic Iterative Monologue paradigm, which coherently interfaces agents with code-based tools, other specialized agents, and human designers. Design acceleration is facilitated by Feature-wise Linear Modulation-conditioned Maxwell surrogate solvers that support the generalized evaluation of metasurface structures. We use freeform dielectric metasurfaces as a model system and demonstrate with MetaChat the design of multiobjective, multiwavelength metasurfaces orders of magnitude faster than conventional methods. These concepts present a scientific computing blueprint for using specialist design agents, surrogate solvers, and human interactions to drive multiphysics innovation and discovery.