Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 3 min ago
PreprintCC BY-NC-NDChemRxiv

Self-Driving Microscopy with Agents: Progress and Prospects

  • Jawad Chowdhury1,2
  • Sumner B Harris1,2
  • Ganesh Narasimha1,2
  • Ondrej Dyck1,2
  • Panchapakesan Ganesh1,2
  • Ruben Millan Solsona1,2
  • Marti Checa1,2
  • Liam Collins1,2
  • Soumendu Bagchi1,2
  • Rama Vasudevan1,2
  • Yongtao Liu1,2
  1. 1Center for Nanophase Materials Sciences
  2. 2Oak Ridge National Laboratory
Open at sourcePDFDOICite

Abstract

Agentic AI, powered by large language models, has increasingly been applied within self-driving laboratories and here we review its emerging role in self-driving microscopy. Microscopy is an unusually demanding target as each experiment is a sequence of interdependent decisions about where to measure, at what resolution, through which modality, and often on ambiguous evidence. We review recent demonstrations across atomic force, scanning tunneling, and transmission electron microscopy and examine how agentic systems can lower the expertise barrier to advanced characterization, transfer strategies between platforms, mine laboratory records for reusable protocols, generate and screen hypotheses, and bring simulation into the experimental loop. We also highlight and examine the limitations that currently constrain these systems. Agents can lose track of the scientific goal as a session outgrows their context window. They also remain poor judges of their own competence, making failure particularly difficult to anticipate in open-ended research. Flexible reasoning must therefore sit on deterministic, physically constrained control, with safety limits enforced outside the model. Human oversight can be the safeguard, but a human acting only as an approval or rejection gate risks forfeiting what scientists contribute most — questioning how the problem was framed in the first place. Designing agentic systems that preserve that contribution and address the current limitations is, in our view, the defining challenge for the field.

Related

  1. Bismuth Chalcogenide‐Based Photocatalysts for Nitrogen Reduction: Recent Progress and Prospects
    Mukesh K. Verma, Muhammad D. Bala, Phindile B. Khoza +2
    Chemistry (Weinheim an Der Bergstrasse, Germany)Peer-reviewedCC BY 4.0Full text1 citedCatalysisPMC
  2. Recent advances in waste-derived sorbents for oil sorption and oil–water separation: progress and future prospects
    Jianliang Mao, Wei Deng, Min Zhao +1
    Separation and Purification TechnologyPeer-reviewedCC BY6 citedMaterials & polymersOpenAlex
  3. Breaking the Triple “Skeleton–Liquid Loading–Liquid Lock” Barrier: Research Progress and Integrated Prospects for Surfactants for Repairing Deep Natural Gas Reservoirs
    Dongxiao Xu, Dingfan Xue, Jingjing Jiang +4
    MoleculesPeer-reviewedCC BY 4.0General chemistryCrossref
  4. What Can the Records of Published Self-Driving Laboratories Predict About a New Platform? A Step-Level Database and Explorer
    Chan Young Joe
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  5. A sustainability-aware self-driving laboratory
    Junyi Zhou, Luyao Ge, Lulu Guo +4
    ChemRxivPreprintCC BY-NC-NDFull textGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{chowdhury2026selfdriving,
  title = {{Self-Driving Microscopy with Agents: Progress and Prospects}},
  author = {Jawad Chowdhury and Sumner B Harris and Ganesh Narasimha and Ondrej Dyck and Panchapakesan Ganesh and Ruben Millan Solsona and Marti Checa and Liam Collins and Soumendu Bagchi and Rama Vasudevan and Yongtao Liu},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15011161/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011161/v1},
  note = {CC BY-NC-ND},
}
RIS
TY  - UNPB
TI  - Self-Driving Microscopy with Agents: Progress and Prospects
AU  - Jawad Chowdhury
AU  - Sumner B Harris
AU  - Ganesh Narasimha
AU  - Ondrej Dyck
AU  - Panchapakesan Ganesh
AU  - Ruben Millan Solsona
AU  - Marti Checa
AU  - Liam Collins
AU  - Soumendu Bagchi
AU  - Rama Vasudevan
AU  - Yongtao Liu
PY  - 2026
DA  - 2026/10/27
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15011161/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011161/v1
AB  - Agentic AI, powered by large language models, has increasingly been applied within self-driving laboratories and here we review its emerging role in self-driving microscopy. Microscopy is an unusually demanding target as each experiment is a sequence of interdependent decisions about where to measure, at what resolution, through which modality, and often on ambiguous evidence. We review recent demonstrations across atomic force, scanning tunneling, and transmission electron microscopy and examine how agentic systems can lower the expertise barrier to advanced characterization, transfer strategies between platforms, mine laboratory records for reusable protocols, generate and screen hypotheses, and bring simulation into the experimental loop. We also highlight and examine the limitations that currently constrain these systems. Agents can lose track of the scientific goal as a session outgrows their context window. They also remain poor judges of their own competence, making failure particularly difficult to anticipate in open-ended research. Flexible reasoning must therefore sit on deterministic, physically constrained control, with safety limits enforced outside the model. Human oversight can be the safeguard, but a human acting only as an approval or rejection gate risks forfeiting what scientists contribute most — questioning how the problem was framed in the first place. Designing agentic systems that preserve that contribution and address the current limitations is, in our view, the defining challenge for the field.
ER  -