An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lu, Darui, Malof, Jordan M., Padilla, Willie J.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912483965403136
author Lu, Darui
Malof, Jordan M.
Padilla, Willie J.
author_facet Lu, Darui
Malof, Jordan M.
Padilla, Willie J.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06935
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design
Lu, Darui
Malof, Jordan M.
Padilla, Willie J.
Artificial Intelligence
Materials Science
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.
title An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design
topic Artificial Intelligence
Materials Science
url https://arxiv.org/abs/2506.06935