Principles and Techniques for Agentic Research in Experimental Physics
Abstract
The use of artificial intelligence (AI) in physics research is increasingly common, yet few guidelines exist for its effective use. Starting with a principles-based approach, we outline a set of ten requirements for collaborative AI agents in experimental physics, spanning scientific norms, effective agent use, and domain expertise. We take a human-centered approach in which agents act as collaborators that amplify rather than replace the expertise of a human researcher (user) who directs the work and is responsible for its results. We then present a framework designed to enforce these requirements, detailing methods for improving off-the-shelf behavior of large language models (LLMs) with custom scaffolding and describing general-purpose scientific workflows and skills. In particular, we highlight the power of closed-loop campaigns where agents work iteratively toward a well-defined goal. We demonstrate the potential of this mode of research through six case studies in experimental physics, covering device design, hardware control, neural network optimization, physical model identification, and data analysis. All six case studies result in useful work products that add utility to our research, including a neural network architecture and solid-state quantum defect photodynamic model that substantially outperform our published work; a microwave waveguide design that extends a published design concept to a fabrication-ready device meeting our experimental constraints; a quantum control pulse sequence candidate that improves simulated performance by more than an order of magnitude; commissioning of an NMR spectrometer to ∼1~Hz frequency precision on live hardware; and finally a data-fitting pipeline that achieves, to our knowledge, the first reconstruction of the Ising microstate of an artificial spin-ice array from diffraction-limited magnetic imaging.
Related
- Thermoreflectance-Based Techniques for Micro- and Nanoscale Thermophysical Property Measurements: Principles, Methods, and Recent Advances
- Reining in an Agentic Harness for High Energy Physics
- SolutionsX: supergravity theories/solutions as code, with an agentic workflow for machine-verifiable physics
- Experimental Evaluation of Passive Polarization Compensation Techniques for Fiber-Distributed Polarization-Entangled Photons
- Discovering Models for Experimental Quantum Systems with Agentic AI
BibTeX
@misc{reed2026principles,
title = {{Principles and Techniques for Agentic Research in Experimental Physics}},
author = {Niko R. Reed and Declan M. Daly and Andrew J. Beling and Jordan D. Giandrea and Ronald L. Walsworth and John W. Blanchard and Daniel Ang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17193},
eprint = {2610.17193},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17193},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Principles and Techniques for Agentic Research in Experimental Physics
AU - Niko R. Reed
AU - Declan M. Daly
AU - Andrew J. Beling
AU - Jordan D. Giandrea
AU - Ronald L. Walsworth
AU - John W. Blanchard
AU - Daniel Ang
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17193
UR - https://arxiv.org/abs/2610.17193
AB - The use of artificial intelligence (AI) in physics research is increasingly common, yet few guidelines exist for its effective use. Starting with a principles-based approach, we outline a set of ten requirements for collaborative AI agents in experimental physics, spanning scientific norms, effective agent use, and domain expertise. We take a human-centered approach in which agents act as collaborators that amplify rather than replace the expertise of a human researcher (user) who directs the work and is responsible for its results. We then present a framework designed to enforce these requirements, detailing methods for improving off-the-shelf behavior of large language models (LLMs) with custom scaffolding and describing general-purpose scientific workflows and skills. In particular, we highlight the power of closed-loop campaigns where agents work iteratively toward a well-defined goal. We demonstrate the potential of this mode of research through six case studies in experimental physics, covering device design, hardware control, neural network optimization, physical model identification, and data analysis. All six case studies result in useful work products that add utility to our research, including a neural network architecture and solid-state quantum defect photodynamic model that substantially outperform our published work; a microwave waveguide design that extends a published design concept to a fabrication-ready device meeting our experimental constraints; a quantum control pulse sequence candidate that improves simulated performance by more than an order of magnitude; commissioning of an NMR spectrometer to ∼1~Hz frequency precision on live hardware; and finally a data-fitting pipeline that achieves, to our knowledge, the first reconstruction of the Ising microstate of an artificial spin-ice array from diffraction-limited magnetic imaging.
ER -