Large language models for human-machine collaborative particle accelerator tuning through natural language
Science Advances · 03.01.2025 · 11 (1)
DOI: 10.1126/sciadv.adr4173 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 03.01.2025. Verfasst von Jan Kaiser und 2 weiteren Autor:innen. Beteiligte Einrichtung: Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Autonomous 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.
Autor:innen und Institutionen
- Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany.
- Universität Hamburg, Hamburg, Germany.
- Hamburg University of Technology, 21073 Hamburg, Germany.
ORCID-Profile: Jan Kaiser, Anne Lauscher, Annika Eichler
Zitieren
APA
Kaiser, J., Lauscher, A., & Eichler, A. (2025). Large language models for human-machine collaborative particle accelerator tuning through natural language. Science Advances, 11(1). https://doi.org/10.1126/sciadv.adr4173
Vancouver
Kaiser J, Lauscher A, Eichler A. Large language models for human-machine collaborative particle accelerator tuning through natural language. Science Advances. 2025;11(1). doi:10.1126/sciadv.adr4173
BibTeX
@article{Kaiser2025,
author = {Kaiser, Jan and Lauscher, Anne and Eichler, Annika},
title = {Large language models for human-machine collaborative particle accelerator tuning through natural language},
journal = {Science Advances},
year = {2025},
volume = {11},
number = {1},
doi = {10.1126/sciadv.adr4173}
}
EUVIMED