用专用语言让人类和AI共同完成高能物理数据分析，代码量减少93%。
HepScript: A Dual-Use DSL for Human-AI Collaborative Data Analysis Workflows in High-Energy Physics
- 设计专用语言HepScript，统一人机协作的数据分析流程。
- 自动从文献生成代码，成功率95%，人工编码减少93%。
- 适合高能物理研究者与想做智能分析的AI开发者。
高能物理实验数据规模持续增长，对分析效率的需求日益迫切。尽管大语言模型（LLMs）为自动化提供了可能，但复杂科学工作流需要深厚领域知识且高度依赖实验特定代码库，导致现有AI难以有效应用。为此，我们提出以HepScript为核心的方法，这是一种面向高能物理（HEP）数据分析的双用途领域专用语言（DSL）。HepScript作为共享形式接口，将分析逻辑抽象为受限语法，既便于人类专家理解，又可被AI代理可靠生成。该语言最初应用于北京谱仪III（BESIII）实验，隐藏底层软件栈复杂性，将高层分析意图转化为生产就绪代码。案例研究表明，该抽象使所需人工编写代码减少93%。关键在于，其受限语法定义了可处理的动作空间，使AI代理能够直接从已发表文献中自主生成核心分析阶段的可执行规范，成功率达95%。本工作展示了人-机协同系统的一条可扩展路径：通过正式指定的DSL，在人类专长、AI自动化与生产环境间建立无歧义的转换层，使此前难以解决的自动化问题得以实现。
原文摘要 · Abstract (English)
The escalating data scale in High-Energy Physics (HEP) fuels a growing aspiration for higher analytical efficiency. While Large Language Models (LLMs) offer a path toward automation via agentic AI, they struggle with complex scientific workflows that require deep domain knowledge and are tightly coupled to experiment-specific codebases. To address this, we introduce a methodology centered on HepScript, a dual-use Domain-Specific Language (DSL) for HEP data analysis workflows. HepScript serves as a shared formal interface, abstracting HEP analysis logic into a constrained syntax that is both intuitive for human experts and reliably generable by AI agents. First developed for the Beijing Spectrometer III (BESIII) experiment, HepScript hides the complexity of the underlying software stack, translating high-level analysis intent into low-level, production-ready code. In our case studies, this abstraction reduces the required human-written code by 93\%. Crucially, HepScript's constrained grammar defines a tractable action space, enabling AI agents to autonomously generate executable specifications for core analysis stages directly from published literature with a 95\% success rate. Our work demonstrates a scalable pathway toward human-AI collaborative systems, where a formally specified DSL acts as an unambiguous translation layer between human expertise, AI automation, and production environment, rendering previously intractable automation problems solvable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。