Research

Paper

TESTING March 05, 2026

Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data

Authors

Anthony Badea, Yi Chen, Yen-Jie Lee

Abstract

We present an AI agentic measurement of the thrust distribution in $e^{+}e^{-}$ collisions at $\sqrt{s}=91.2$~GeV using archived ALEPH data. The analysis and all note writing is carried out entirely by AI agents (OpenAI Codex and Anthropic Claude) under expert physicist direction. A fully corrected spectrum is obtained via Iterative Bayesian Unfolding and Monte Carlo based corrections. This work represents a step toward a theory-experiment loop in which AI agents assist with experimental measurements and theoretical calculations, and synthesize insights by comparing the results, thereby accelerating the cycle that drives discovery in fundamental physics. Our work suggests that precision physics, leveraging the open LEP data and advanced theoretical landscape, provides an ideal testing ground for developing advanced AI systems for scientific applications.

Metadata

arXiv ID: 2603.05735
Provider: ARXIV
Primary Category: hep-ex
Published: 2026-03-05
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05735v1</id>\n    <title>Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data</title>\n    <updated>2026-03-05T22:48:06Z</updated>\n    <link href='https://arxiv.org/abs/2603.05735v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05735v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We present an AI agentic measurement of the thrust distribution in $e^{+}e^{-}$ collisions at $\\sqrt{s}=91.2$~GeV using archived ALEPH data. The analysis and all note writing is carried out entirely by AI agents (OpenAI Codex and Anthropic Claude) under expert physicist direction. A fully corrected spectrum is obtained via Iterative Bayesian Unfolding and Monte Carlo based corrections. This work represents a step toward a theory-experiment loop in which AI agents assist with experimental measurements and theoretical calculations, and synthesize insights by comparing the results, thereby accelerating the cycle that drives discovery in fundamental physics. Our work suggests that precision physics, leveraging the open LEP data and advanced theoretical landscape, provides an ideal testing ground for developing advanced AI systems for scientific applications.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='hep-ex'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='hep-ph'/>\n    <published>2026-03-05T22:48:06Z</published>\n    <arxiv:primary_category term='hep-ex'/>\n    <author>\n      <name>Anthony Badea</name>\n    </author>\n    <author>\n      <name>Yi Chen</name>\n    </author>\n    <author>\n      <name>Yen-Jie Lee</name>\n    </author>\n  </entry>"
}