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

arXiv cs.AI / 4/2/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

Key Points

  • The paper demonstrates an agentic AI approach to measuring the thrust distribution in e+e− collisions at 91.2 GeV using archived ALEPH data from LEP.
  • It reports that AI agents (OpenAI Codex and Anthropic Claude), with guidance from expert physicists, performed the analysis and note writing end-to-end as a proof of concept.
  • The authors obtain a fully corrected thrust spectrum using Iterative Bayesian Unfolding combined with Monte Carlo–based correction procedures.
  • They frame the result as a step toward an integrated theory–experiment loop where AI agents help connect experimental measurements with theoretical calculations to speed scientific discovery.
  • The work positions open LEP data and a mature theoretical landscape as an effective testbed for developing more advanced AI systems for precision science.

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.