Hierarchical automation of scanning probe microscopy through agentic orchestration and algorithmic control
Abstract
Rapid advances in agentic artificial intelligence enable scientific systems to interpret open-ended objectives, combine heterogeneous information, invoke specialized tools, and revise experimental strategies as evidence accumulates. However, physical experimentation also contains many tasks for which agentic reasoning provides little advantage and can reduce reliability. Quantitative analysis, optimization, spatial targeting, validation, and instrument execution are often better posed as deterministic or algorithmic operations with explicit objectives and verifiable outputs. Here, we introduce a hierarchical architecture for autonomous experimentation that separates these roles. Agentic components interpret scientific intent, construct task-dependent experimental representations, evaluate accumulated evidence, and select high-level actions, whereas deterministic algorithms perform numerical analysis, coordinate selection, validation, and physical execution. We implement this architecture in piezoresponse force microscopy. Starting from a broad scientific question concerning the relation between local domain structure and polarization switching, the system constructs spatial descriptors from multichannel imaging, selects and analyzes local hysteresis measurements, adapts the spectroscopy waveform, and terminates the experiment when additional measurements cease to provide new evidence. The autonomous trajectory also identifies a confounding relationship between polarization state and domain-wall proximity and recognizes that the requested contrast is not independently represented within the available field of view. These results demonstrate a route toward scientific autonomy in which agents determine what evidence is required while algorithms determine how that evidence is acquired reproducibly and within validated physical constraints.
Related
- Enhanced nanometer-scale linewidth metrology using dark-field through-focus scanning optical microscopy
- Parametrized Relativistic Quantum Theory: Framework and Application to Scanning Tunneling Microscopy
- Scanning through space and time: past, present, and future of time-resolved scanning transmission soft X-ray microscopy
- Multi-Angle Beam Scanning Transmission Electron Microscopy for Diffraction-Contrast-Free Magnetic Imaging
- STEM-Bank-26: An Open Dataset of Analytical Scanning Transmission Electron Microscopy Images and Spectra
BibTeX
@misc{slautin2026hierarchical,
title = {{Hierarchical automation of scanning probe microscopy through agentic orchestration and algorithmic control}},
author = {Boris N. Slautin and Sheryl L. Sanchez and Aidan Swanger and Yu Liu and Gerd Duscher and Vladimir V. Shvartsman and Mahshid Ahmadi and Sergei V. Kalinin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04015},
eprint = {2609.04015},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04015},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Hierarchical automation of scanning probe microscopy through agentic orchestration and algorithmic control
AU - Boris N. Slautin
AU - Sheryl L. Sanchez
AU - Aidan Swanger
AU - Yu Liu
AU - Gerd Duscher
AU - Vladimir V. Shvartsman
AU - Mahshid Ahmadi
AU - Sergei V. Kalinin
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.04015
UR - https://arxiv.org/abs/2609.04015
AB - Rapid advances in agentic artificial intelligence enable scientific systems to interpret open-ended objectives, combine heterogeneous information, invoke specialized tools, and revise experimental strategies as evidence accumulates. However, physical experimentation also contains many tasks for which agentic reasoning provides little advantage and can reduce reliability. Quantitative analysis, optimization, spatial targeting, validation, and instrument execution are often better posed as deterministic or algorithmic operations with explicit objectives and verifiable outputs. Here, we introduce a hierarchical architecture for autonomous experimentation that separates these roles. Agentic components interpret scientific intent, construct task-dependent experimental representations, evaluate accumulated evidence, and select high-level actions, whereas deterministic algorithms perform numerical analysis, coordinate selection, validation, and physical execution. We implement this architecture in piezoresponse force microscopy. Starting from a broad scientific question concerning the relation between local domain structure and polarization switching, the system constructs spatial descriptors from multichannel imaging, selects and analyzes local hysteresis measurements, adapts the spectroscopy waveform, and terminates the experiment when additional measurements cease to provide new evidence. The autonomous trajectory also identifies a confounding relationship between polarization state and domain-wall proximity and recognizes that the requested contrast is not independently represented within the available field of view. These results demonstrate a route toward scientific autonomy in which agents determine what evidence is required while algorithms determine how that evidence is acquired reproducibly and within validated physical constraints.
ER -