HepScript: A Dual-Use DSL for Human-AI Collaborative Data Analysis Workflows in High-Energy Physics

2026-05-05 · Source: cs.MA updates on arXiv.org · Field: Science & Research — Physical Sciences & Chemistry, Mathematics & Computational Sciences, Research Methodology & Innovation · Depth: Expert, quick

Summary

HepScript is a novel dual-use Domain-Specific Language (DSL) designed to enhance human-AI collaborative data analysis workflows in High-Energy Physics (HEP). Developed initially for the Beijing Spectrometer III (BESIII) experiment, HepScript abstracts complex HEP analysis logic into a constrained, intuitive syntax. This DSL serves as a formal interface, enabling both human experts to express high-level analysis intent and AI agents to reliably generate executable specifications. By hiding the underlying software stack's complexity, HepScript reduces human-written code by 93%. Its constrained grammar defines a tractable action space, allowing AI agents to autonomously generate core analysis stages directly from published literature with a 95% success rate, addressing the challenges LLMs face with complex scientific workflows requiring deep domain knowledge.

Key takeaway

For High-Energy Physics researchers and AI scientists developing agentic systems, HepScript demonstrates a scalable pathway to integrate AI into complex data analysis. Consider adopting or developing similar DSLs to create unambiguous translation layers between human expertise, AI automation, and production environments, thereby solving previously intractable automation problems and significantly reducing manual coding effort.

Key insights

HepScript DSL enables human-AI collaboration in HEP by abstracting complex analysis into a constrained, AI-generable syntax.

Principles

• Constrained DSLs improve AI agent reliability.
• Abstraction simplifies complex scientific workflows.

Method

HepScript abstracts HEP analysis logic into a formal, constrained DSL. This DSL translates high-level intent into low-level code, enabling AI agents to generate executable specifications from literature.

In practice

• Reduce human-written code by 93%.
• Achieve 95% AI generation success rate.

Topics

• HepScript
• High-Energy Physics
• Domain-Specific Language
• Human-AI Collaboration
• Large Language Models

Best for: AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

• PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research — PRL-Bench evaluates LLMs' end-to-end physics research capabilities, revealing significant performance gaps.
• What I’ve learned from 25 years of automated science, and what the future holds: an interview with Ross King — AI-driven automated science and DNA computing offer pathways to dramatically accelerate scientific discovery and address global challenges.
• Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks — An AI agent harness automates end-to-end visual analysis application design, bridging data to interactive interfaces.
• From Data to Theory: Autonomous Large Language Model Agents for Materials Science — Autonomous LLM agents can perform end-to-end scientific theory development, from equation selection to code execution and validation.
• Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software — Effective human supervision, not just AI capability, is crucial for trustworthy scientific software development.
• EinsteinArena: Harnessing the collective intelligence of agents in the wild to advance science — Collective AI agent platforms accelerate scientific discovery by enabling collaboration and iterative problem-solving.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.MA updates on arXiv.org.