Science Advances · 2025 · 11 citations · 13 references
ComputingComputer SciencePhysicsArtificial IntelligenceMachine LearningOptimizationAccelerator PhysicsLanguage ModelingLanguage ModelsNatural Language UnderstandingOptimization For Machine LearningReinforcement LearningAcceleratorsBayesian OptimizationLanguage Model Fine-tuningLarge Language ModelsLarge-scale Natural Language ProcessingOptimization AlgorithmsReinforcement Optimization
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.
13
HellaSwag: Can a Machine Really Finish Your Sentence?
Rowan Zellers, Ari Holtzman, Yonatan Bisk et al. · 2019 · 707 citations · Full text
Mathematical discoveries from program search with large language models
Bernardino Romera‐Paredes, Mohammadamin Barekatain, Alexander Novikov et al. · Nature · 2023 · 346 citations · Full text
Learning to Optimize: A Primer and A Benchmark
Tianlong Chen, Xiaohan Chen, Wuyang Chen et al. · arXiv (Cornell University) · 2021 · 92 citations · Full text
Bayesian optimization algorithms for accelerator physics
Ryan Roussel, Auralee Edelen, Tobias Boltz et al. · Physical Review Accelerators and Beams · 2024 · 64 citations · Full text