Agentic inverse design of spatially programmed materials
Abstract
Spatially programmed functional materials, from functionally graded alloys and metamaterials to quantum superlattices, use their spatial structure to tailor physical properties. However, translating a desired spatial structure into a practical fabrication recipe remains challenging due to the complex relationship between processing conditions and resulting material structures. Here we show that a large language model (LLM) agent can inverse-design such fabrication recipes by using a physics-based simulator of ion-matter interactions as a tool. Given an arbitrary depth profile of implanted ions or vacancies, the agent selects the ion species, energies, incident angles, and target material layers; writes, runs, and interprets simulations; and iteratively refines the recipe until the simulated profile matches the target, with minimal human input. Our work demonstrates physics-guided agentic inverse design as a practical approach to making the spatial structure of materials a programmable variable, opening new opportunities to explore emergent physical phenomena and functional phases of matter.
Related
- Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Design
- Probing the limits of forward screening and inverse design of crystal materials
- ALIGNN 2.0: A Unified Line-Graph Neural Network Framework for Materials Screening, Force Fields, Inverse Design, Spectroscopy, and Microscopy
- Polarity-Programmed Topological Gating of Knotting in Spatially Patterned Active Polymers
- Agentic programs: an emerging form of scientific software in computational materials science
BibTeX
@misc{carrizales2026agentic,
title = {{Agentic inverse design of spatially programmed materials}},
author = {Denisse Córdova Carrizales and Abhijatmedhi Chotrattanapituk and L. Dagny Davis and Jeremy Ramsey and Ryotaro Okabe and Mouyang Cheng and Mingda Li},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03795},
eprint = {2611.03795},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03795},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic inverse design of spatially programmed materials
AU - Denisse Córdova Carrizales
AU - Abhijatmedhi Chotrattanapituk
AU - L. Dagny Davis
AU - Jeremy Ramsey
AU - Ryotaro Okabe
AU - Mouyang Cheng
AU - Mingda Li
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.03795
UR - https://arxiv.org/abs/2611.03795
AB - Spatially programmed functional materials, from functionally graded alloys and metamaterials to quantum superlattices, use their spatial structure to tailor physical properties. However, translating a desired spatial structure into a practical fabrication recipe remains challenging due to the complex relationship between processing conditions and resulting material structures. Here we show that a large language model (LLM) agent can inverse-design such fabrication recipes by using a physics-based simulator of ion-matter interactions as a tool. Given an arbitrary depth profile of implanted ions or vacancies, the agent selects the ion species, energies, incident angles, and target material layers; writes, runs, and interprets simulations; and iteratively refines the recipe until the simulated profile matches the target, with minimal human input. Our work demonstrates physics-guided agentic inverse design as a practical approach to making the spatial structure of materials a programmable variable, opening new opportunities to explore emergent physical phenomena and functional phases of matter.
ER -