arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06336physics.acc-phcs.AI
收藏

面向粒子加速器的智能体式AI

Towards Agentic AI on Particle Accelerators

Helmholtz Zentrum Berlin(柏林海德堡中心);LBNL(劳伦斯伯克利国家实验室);DESY(德意志电子同步辐射研究中心);FNAL(费米国家加速器实验室)

Antonin Sulc, Thorsten Hellert, Raimund Kammering, Hayden Hoschouer, Jason St. John

AI总结:

针对粒子加速器复杂度提升带来的控制难题,提出由LLM驱动的去中心化多智能体控制框架,各智能体分管组件、可通过经验与人反馈自改进,还探讨相关问题并以三示例验证架构可行性。

摘要:

随着粒子加速器复杂度不断提升,传统控制方法在实现最优性能方面面临的挑战日益加剧。本文提出了一种范式转变:一种用于加速器控制的去中心化多智能体框架,该框架以大语言模型(Large Language Models, LLMs)为支撑,分布在多个自主智能体之间。我们提出了一种自改进去中心化系统的构想,其中智能体负责处理高层任务与通信,且每个智能体专门用于控制单个加速器组件。这一方法引发了若干问题:AI在粒子加速器中的未来应用有哪些?我们如何实现像粒子加速器这样的自主复杂系统,让智能体通过经验和人类反馈逐步改进?将“人在回路”组件用于标注运行数据并提供专家指导,其集成会带来哪些影响?我们展示了三个示例,证明了此类架构的可行性。

英文摘要:

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show three examples, where we demonstrate the viability of such architecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑