An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design

TL;DR

This paper presents an agentic framework that autonomously designs photonic metamaterials by integrating LLMs, external tools, and deep learning, enabling complex inverse design tasks with reasoning and adaptability.

Contribution

It introduces a novel autonomous framework combining LLMs, external APIs, and deep learning for inverse metamaterial design, showcasing reasoning and adaptability.

Findings

Automates the inverse design process for photonic metamaterials.

Demonstrates reasoning, planning, and adaptation capabilities.

Produces potentially novel metamaterial designs.

Abstract

Recent significant advances in integrating multiple Large Language Model (LLM) systems have enabled Agentic Frameworks capable of performing complex tasks autonomously, including novel scientific research. We develop and demonstrate such a framework specifically for the inverse design of photonic metamaterials. When queried with a desired optical spectrum, the Agent autonomously proposes and develops a forward deep learning model, accesses external tools via APIs for tasks like simulation and optimization, utilizes memory, and generates a final design via a deep inverse method. The framework's effectiveness is demonstrated in its ability to automate, reason, plan, and adapt. Notably, the Agentic Framework possesses internal reflection and decision flexibility, permitting highly varied and potentially novel outputs.