发表机构
Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出语言模型智能体闭环循环，自主发现加速器调试算法，在ALS-U储存环射频束流捕获任务中取得良好效果，生成多目标非支配算法，推动调试研究模式转变。
AI 中文摘要
模拟调试已成为降低现代光源设计与调试风险的关键，但被模拟的流程仍完全由人类专家设计。晶格变更后需进行劳动密集型的重新开发，导致此类研究难以重复，并限制了其在早期设计迭代中的应用。本文展示了一种闭环研究循环：语言模型智能体编写调试代码，在模拟中测试，并根据结果改进算法。将该循环应用于ALS-U储存环模型中的射频束流捕获，其大幅改进了专家设计的可行流程，且能从极简起点构建出可行流程，能力更强的模型可从更少初始代码中成功。将同一框架扩展至多目标，生成了16种非支配算法，涵盖快速束流捕获与种子机器误差校正之间物理上截然不同的权衡。这将调试研究从评估人类设计流程，转变为智能体直接参与发现加速器算法的模式。
英文摘要
Simulated commissioning has become essential for de-risking modern light-source design and commissioning, but the procedures being simulated are still designed entirely by human experts. Their labor-intensive redevelopment after lattice changes makes such studies hard to repeat and limits their use during early design iteration. This Letter demonstrates a closed research loop in which a language-model agent writes commissioning code, tests it in simulation, and improves the algorithm from the results. Applied to RF beam capture in the ALS-U accumulator-ring model, the loop substantially improves a working expert procedure and can construct a working one from a minimal starting point, with more capable models succeeding from less initial code. Extending the same framework to multiple objectives produces 16 non-dominated algorithms spanning physically distinct trade-offs between rapid beam capture and correction of seeded machine errors. This reframes commissioning studies from evaluating human-designed procedures toward a mode in which agents participate directly in discovering accelerator algorithms.
Comments9 pages, 4 figures. Submitted to Physical Review Accelerators and Beams (ZVR1001)
