English

EasyScan_HEP 2: Agent-Ready Parameter Scans for High-Energy Physics

High Energy Physics - Phenomenology 2026-06-30 v1

Abstract

AI agents are beginning to reshape the preparation and steering of computational workflows in high-energy physics phenomenology. To accommodate this change, we upgrade EasyScan_HEP to make the construction of parameter-scan configuration files more accessible to AI assistance. EasyScan_HEP 2 exposes agent-facing command-line and machine-readable interfaces, allowing an assistant to translate natural language requests into an explicit .ini configuration that defines the scan method, external-program workflow, constraints, and outputs. The resulting configuration can be inspected through a local Web UI. The framework also supports AI-assisted extension to new scan methods, as illustrated by the integration of BESTFIT, EMCEE, and DYNESTY. In this way, EasyScan_HEP 2 adapts parameter scans to AI-assisted workflows while preserving reproducibility, transparency, and user control.

Cite

@article{arxiv.2606.31214,
  title  = {EasyScan_HEP 2: Agent-Ready Parameter Scans for High-Energy Physics},
  author = {Yang Xiao and Yuanfang Yue and Yang Zhang},
  journal= {arXiv preprint arXiv:2606.31214},
  year   = {2026}
}

Comments

16 pages, 3 figures

R2 v1 2026-07-22T20:18:11.440Z