# Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Language

arXiv: https://arxiv.org/abs/2405.08888 · HTML: https://mlsanity.com/paper/2405.08888/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 14 May 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Learning to Optimize](https://mlsanity.com/paper/1606.01885/) (2016)
- [Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models](https://mlsanity.com/paper/2304.03271/) (2023)
- [Learning to Optimize Neural Nets](https://mlsanity.com/paper/1703.00441/) (2017)
- [LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments](https://mlsanity.com/paper/2403.08337/) (2024)
- [Autonomous Control of a Particle Accelerator using Deep Reinforcement Learning](https://mlsanity.com/paper/2010.08141/) (2020)
- [PACuna: Automated Fine-Tuning of Language Models for Particle Accelerators](https://mlsanity.com/paper/2310.19106/) (2023)

## Built on by (most cited first, 9 of 9)

- [Can Theoretical Physics Research Benefit from Language Agents?](https://mlsanity.com/paper/2506.06214/) (2025)
- [Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator](https://mlsanity.com/paper/2509.17255/) (2025)
- [Towards Unlocking Insights from Logbooks Using AI](https://mlsanity.com/paper/2406.12881/) (2024)
- [Agents of Discovery](https://mlsanity.com/paper/2509.08535/) (2025)
- [SelfAI: A self-directed framework for long-horizon scientific discovery](https://mlsanity.com/paper/2512.00403/) (2025)
- [Optimisation of the Accelerator Control by Reinforcement Learning: A Simulation-Based Approach](https://mlsanity.com/paper/2503.09665/) (2025)
- [Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination](https://mlsanity.com/paper/2607.08403/) (2026)
- [A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility](https://mlsanity.com/paper/2607.24663/) (2026)
- [Vision-Language Agents for Active Perception in Optics Laboratories](https://mlsanity.com/paper/2609.32918/) (2026)

## Abstract (arXiv)

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.