000617676 001__ 617676
000617676 005__ 20250715151509.0
000617676 0247_ $$2INSPIRETeX$$aKaiser:2024lkg
000617676 0247_ $$2inspire$$ainspire:2787129
000617676 0247_ $$2arXiv$$aarXiv:2405.08888
000617676 0247_ $$2doi$$a10.1126/sciadv.adr4173
000617676 0247_ $$2datacite_doi$$a10.3204/PUBDB-2024-06977
000617676 0247_ $$2altmetric$$aaltmetric:172607705
000617676 0247_ $$2pmid$$apmid:39742494
000617676 0247_ $$2WOS$$aWOS:001386432700013
000617676 0247_ $$2openalex$$aopenalex:W4405967751
000617676 037__ $$aPUBDB-2024-06977
000617676 041__ $$aEnglish
000617676 082__ $$a500
000617676 1001_ $$0P:(DE-H253)PIP1095111$$aKaiser, Jan$$b0$$eCorresponding author
000617676 245__ $$aLarge language models for human-machine collaborative particle accelerator tuning through natural language
000617676 260__ $$aWashington, DC [u.a.]$$bAssoc.$$c2025
000617676 3367_ $$2DRIVER$$aarticle
000617676 3367_ $$2DataCite$$aOutput Types/Journal article
000617676 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1736343003_3333182
000617676 3367_ $$2BibTeX$$aARTICLE
000617676 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000617676 3367_ $$00$$2EndNote$$aJournal Article
000617676 520__ $$aAutonomous tuning of particle accelerators is an active and challenging research field with the goal of enabling advanced accelerator technologies and cutting-edge high-impact applications, such as physics discovery, cancer research, and material sciences. A challenge with autonomous accelerator tuning remains that the most capable algorithms require experts in optimization and machine learning to implement them for every new tuning task. Here, we propose the use of large language models (LLMs) to tune particle accelerators. We demonstrate on a proof-of-principle example the ability of LLMs to tune an accelerator subsystem based on only a natural language prompt from the operator, and compare their performance to state-of-the-art optimization algorithms, such as Bayesian optimization and reinforcement learning–trained optimization. In doing so, we also show how LLMs can perform numerical optimization of a nonlinear real-world objective. Ultimately, this work represents another complex task that LLMs can solve and promises to help accelerate the deployment of autonomous tuning algorithms to day-to-day particle accelerator operations.
000617676 536__ $$0G:(DE-HGF)POF4-621$$a621 - Accelerator Research and Development (POF4-621)$$cPOF4-621$$fPOF IV$$x0
000617676 536__ $$0G:(DE-HGF)2020_InternLabs-0011$$aInternLabs-0011 - HIR3X - Helmholtz International Laboratory on Reliability, Repetition, Results at the most advanced X-ray Sources (2020_InternLabs-0011)$$c2020_InternLabs-0011$$x1
000617676 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000617676 693__ $$0EXP:(DE-H253)ARES-20200101$$1EXP:(DE-H253)SINBAD-20200101$$5EXP:(DE-H253)ARES-20200101$$aSINBAD$$eAccelerator Research Experiment at SINBAD$$x0
000617676 7001_ $$0P:(DE-HGF)0$$aLauscher, Anne$$b1
000617676 7001_ $$0P:(DE-H253)PIP1087213$$aEichler, Annika$$b2
000617676 773__ $$0PERI:(DE-600)2810933-8$$a10.1126/sciadv.adr4173$$gVol. 11, no. 1, p. eadr4173$$n1$$peadr4173$$tScience advances$$v11$$x2375-2548$$y2025
000617676 7870_ $$0PUBDB-2024-01644$$aKaiser, Jan et.al.$$d2024$$iIsParent$$rarXiv:2405.08888$$tLarge Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Language
000617676 8564_ $$uhttps://doi.org/10.1126/sciadv.adr4173
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/HTML-Approval_of_scientific_publication.html
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/Invoice.pdf
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/PDF-Approval_of_scientific_publication.pdf
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/Invoice.pdf?subformat=pdfa$$xpdfa
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/publisher%27s%20fulltext.pdf$$yOpenAccess
000617676 8564_ $$uhttps://bib-pubdb1.desy.de/record/617676/files/publisher%27s%20fulltext.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000617676 8767_ $$8APC600600914$$92024-11-21$$a52907480$$d2024-11-27$$eAPC$$jZahlung erfolgt$$v37.84$$zCorresponding author: J. Kaiser
000617676 8767_ $$81$$92024-11-21$$a52907480$$d2024-11-27$$eAPC$$jStorniert$$zDFG OAPK (Projekt)
000617676 8767_ $$81$$92024-11-21$$a52907480$$d2024-11-27$$eAPC$$jZahlung erfolgt$$zDFG OAPK (Projekt)
000617676 909CO $$ooai:bib-pubdb1.desy.de:617676$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000617676 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1095111$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000617676 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1087213$$aDeutsches Elektronen-Synchrotron$$b2$$kDESY
000617676 9101_ $$0I:(DE-588)1043621512$$6P:(DE-H253)PIP1087213$$aEuropean XFEL$$b2$$kXFEL.EU
000617676 9131_ $$0G:(DE-HGF)POF4-621$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vAccelerator Research and Development$$x0
000617676 9141_ $$y2025
000617676 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-28
000617676 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000617676 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-28
000617676 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-08-28
000617676 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000617676 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-08-28
000617676 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSCI ADV : 2022$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-05-14T07:33:42Z
000617676 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-05-14T07:33:42Z
000617676 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-05-14T07:33:42Z
000617676 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18
000617676 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bSCI ADV : 2022$$d2024-12-18
000617676 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000617676 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000617676 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000617676 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000617676 9201_ $$0I:(DE-H253)MSK-20120731$$kMSK$$lStrahlkontrollen$$x0
000617676 980__ $$ajournal
000617676 980__ $$aVDB
000617676 980__ $$aUNRESTRICTED
000617676 980__ $$aI:(DE-H253)MSK-20120731
000617676 980__ $$aAPC
000617676 9801_ $$aAPC
000617676 9801_ $$aFullTexts