Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data
For experimental particle physics, this proof-of-concept shows that AI agents can autonomously execute complex data analysis tasks, potentially accelerating the discovery cycle in fundamental physics.
This work demonstrates an AI agentic measurement of the thrust distribution in e+e- collisions at 91.2 GeV using LEP open data, where AI agents performed the entire analysis and note writing under physicist supervision, achieving a fully corrected spectrum via Iterative Bayesian Unfolding.
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.