Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 47 min ago
PreprintCC BY 4.0arXiv

Integration of Retrieval-Augmented Generation for Knowledge Access in the ELBE Accelerator Control System

  • Najmeh Mirian
Open at sourcePDFDOICite

Abstract

The efficient operation of accelerator facilities increas- ingly relies on rapid access to heterogeneous operational knowledge, including logbooks, interlock reports, machine parameters, and historical archive data. At ELBE, we pro- posed a Retrieval-Augmented Generation (RAG) frame- work that integrates facility documentation and operational records into a unified AI-assisted support tool for operators. The system is expected to index electronic logbooks, ma- chine archive time-series data, and subsystem manuals using domain-adapted embeddings stored in a vector database. User queries will be expected to be processed through a large language model that retrieves the most relevant oper- ational context and generates structured, operator-oriented responses with traceable source references. This contribu- tion presents the system architecture, data integration strat- egy, and challenges toward real-time AI-assisted accelerator operation

Related

  1. Towards Retrieval Augmented Generation in High-Energy and Astroparticle Physics
    Jacky Kumar, Sajan Kumar
    arXivPreprintCC BY 4.0Full textHigh-energy astrophysicsHigh-energy & particle physicsarXiv
  2. Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Experiment Tracking
    Mahee Gamage, Vlad Stirbu
    arXivPreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv
  3. chATLAS: A Retrieval-Augmented Conversational Assistant for the ATLAS Experiment
    Joe Egan, Ben Elliot, Samuel Van Stroud +11
    arXivPreprintCC BY 4.0Full textHigh-energy & particle physicsarXivHAL
  4. Knowledge-Driven XRD Phase Identification via Multi-View Retrieval and Explanation
    Doaa Mohamed, Markus Stricker
    arXivPreprintCC BY-SA 4.0Full textCondensed matterarXiv
  5. Overlap and topology shape synergy in collective knowledge integration
    Daeseong Kim, Masato S. Abe
    arXivPreprintCC BY 4.0Full textStatistical & nonlinear physicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{mirian2026integration,
  title = {{Integration of Retrieval-Augmented Generation for Knowledge Access in the ELBE Accelerator Control System}},
  author = {Najmeh Mirian},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.27579},
  eprint = {2609.27579},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27579},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Integration of Retrieval-Augmented Generation for Knowledge Access in the ELBE Accelerator Control System
AU  - Najmeh Mirian
PY  - 2026
DA  - 2026/09/23
PB  - arXiv
DO  - 10.48550/arxiv.2609.27579
UR  - https://arxiv.org/abs/2609.27579
AB  - The efficient operation of accelerator facilities increas- ingly relies on rapid access to heterogeneous operational knowledge, including logbooks, interlock reports, machine parameters, and historical archive data. At ELBE, we pro- posed a Retrieval-Augmented Generation (RAG) frame- work that integrates facility documentation and operational records into a unified AI-assisted support tool for operators. The system is expected to index electronic logbooks, ma- chine archive time-series data, and subsystem manuals using domain-adapted embeddings stored in a vector database. User queries will be expected to be processed through a large language model that retrieves the most relevant oper- ational context and generates structured, operator-oriented responses with traceable source references. This contribu- tion presents the system architecture, data integration strat- egy, and challenges toward real-time AI-assisted accelerator operation
ER  -