Options
Agentic AI for user facilities: workshop report
Citation Link: https://doi.org/10.15480/882.17066
Publikationstyp
Journal Article
Date Issued
2026-04-21
Sprache
English
Author(s)
Barnard, Edward S.
Dunn, Tim J.
Machado Gazolla, Joao Gabriel Felipe
Grbcic, Luka
Jinghua, Guo
Ha, Yang
Hexemer, Alexander
Xiangyang, Ju
Pérez, Gabriel E.
Quinn, Paul
Rafique, Haroon
Reed, Aaron
Reyes, Eno
Shang, Hairong
Smith, Martin
Tennant, Chris
Tripathi, Pawan K.
Underwood, Robert
Wall, Morgan
Wu, Amy
Yager, Kevin G.
TORE-DOI
Journal
Citation
Synchrotron Radiation News (in Press): (2026)
Publisher DOI
Scopus ID
Publisher
Taylor & Francis
This workshop addressed a gap: the most recent DOE reports on AI for science [1–3] predate recent advances in agentic AI—LLMbased systems that can plan, orchestrate, and execute multi-step workflows. With 100 participants from eight US DOE facilities and two allied facilities across accelerators, beamlines, nanoscience, genomics/biology, and computing infrastructure, this report identifies paths to deploy agentic AI at DOE user facilities while preserving safety, accountability, and rigor. Discussions also reflected DOE’s Genesis mission emphasis on end-to-end workflow acceleration through integrated data, computing, and AI capabilities.
DDC Class
006.3: Artificial Intelligence
005: Computer Programming, Programs, Data and Security
620: Engineering
Publication version
publishedVersion
Loading...
Name
Agentic AI for User Facilities Workshop Report.pdf
Type
Main Article
Size
1.25 MB
Format
Adobe PDF