物理与工程2026，Vol.46Issue(5)：38-44,7.DOI:10.27024/j.wlygc.2026.08.13.is
以人工智能窥探粒子的奥秘
PROBING PARTICLE PHYSICS WITH ARTIFICIAL INTELLIGENCE
摘要
Abstract
Particle physics experiments have long research cycles and high barriers to entry.Limited human resources make it difficult to fully explore and analyze large volumes of colli-sion data.Agents based on large language models can write code,retrieve literature,and car-ry out multi-step analyses,offering an opportunity to address this challenge.This article fo-cuses on the Just Furnish Context(JFC)agent framework and examines results produced by the framework,including the CMS H→τ+τ-signal-strength measurement and the ALEPH Lund jet-plane density measurement,as well as their implications for particle physics re-search.It also summarizes the framework's current limitations and discusses prospects for benchmark-dataset construction,data processing at next-generation large-scale scientific facili-ties,and the training of future physicists.关键词
粒子物理/高能物理实验/人工智能/大语言模型/智能体Key words
particle physics/high energy physics experiment/artificial intelligence/large lan-guage models/AI agents引用本文复制引用
赵一扬,胡震..以人工智能窥探粒子的奥秘[J].物理与工程,2026,46(5):38-44,7.基金项目
本工作得到国家自然科学基金项目W2511007、125B1008,清华大学自主科研计划的支持. （）
