% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Kaiser:606814,
author = {Kaiser, Jan and Eichler, Annika and Lauscher, Anne},
title = {{L}arge {L}anguage {M}odels for {H}uman-{M}achine
{C}ollaborative {P}article {A}ccelerator {T}uning through
{N}atural {L}anguage},
reportid = {PUBDB-2024-01644, arXiv:2405.08888},
year = {2024},
note = {22 pages, 5 figures},
abstract = {Autonomous tuning of particle accelerators is an active and
challenging field of research with the goal of enabling
novel accelerator technologies cutting-edge high-impact
applications, such as physics discovery, cancer research and
material sciences. A key challenge with autonomous
accelerator tuning remains that the most capable algorithms
require an expert in optimisation, machine learning or a
similar field to implement the algorithm for every new
tuning task. In this work, 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 successfully and autonomously tune a particle
accelerator subsystem based on nothing more than a natural
language prompt from the operator, and compare the
performance of our LLM-based solution to state-of-the-art
optimisation algorithms, such as Bayesian optimisation (BO)
and reinforcement learning-trained optimisation (RLO). In
doing so, we also show how LLMs can perform numerical
optimisation of a highly non-linear real-world objective
function. Ultimately, this work represents yet another
complex task that LLMs are capable of solving and promises
to help accelerate the deployment of autonomous tuning
algorithms to the day-to-day operations of particle
accelerators.},
cin = {MSK},
cid = {I:(DE-H253)MSK-20120731},
pnm = {621 - Accelerator Research and Development (POF4-621) /
InternLabs-0011 - HIR3X - Helmholtz International Laboratory
on Reliability, Repetition, Results at the most advanced
X-ray Sources $(2020_InternLabs-0011)$},
pid = {G:(DE-HGF)POF4-621 / $G:(DE-HGF)2020_InternLabs-0011$},
experiment = {EXP:(DE-H253)ARES-20200101},
typ = {PUB:(DE-HGF)25},
eprint = {2405.08888},
howpublished = {arXiv:2405.08888},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2405.08888;\%\%$},
doi = {10.3204/PUBDB-2024-01644},
url = {https://bib-pubdb1.desy.de/record/606814},
}