Saved in:
Bibliographic Details
Main Authors: Alexander, Stephon, Bradley, Benjamin, Gouskos, Loukas, Niu, Cooper
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.28935
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914432987168768
author Alexander, Stephon
Bradley, Benjamin
Gouskos, Loukas
Niu, Cooper
author_facet Alexander, Stephon
Bradley, Benjamin
Gouskos, Loukas
Niu, Cooper
contents The search for physics beyond the Standard Model is hindered by a combinatorial explosion of possible theories. We introduce \textsc{Albert}, a neuro-symbolic artificial intelligence framework to systematically navigate this vast theory space. By encoding particle physics as a formal language, \textsc{Albert} generates tokenized sequences representing symmetries, particles, and interactions under a rule-based grammar, eliminating the hallucinations common in large language models. The reinforcement learning environment enforces first-principle theoretical constraints, computes observables with radiative corrections, and evaluates statistical likelihood via $χ^2$ analysis against experimental data. As a proof of concept, we train a 25-million-parameter transformer model using only legacy data from the Large Electron-Positron Collider, which contains no direct evidence of the top quark. Remarkably, \textsc{Albert} successfully rediscovered the Standard Model and autonomously inferred necessity and properties of the top quark, predicting its mass at $178.9\pm 5.0~\text{GeV}$, consistent with its modern measurement at the Large Hadron Collider. These results demonstrate the potential of AI-driven theory exploration as a rigorous, hallucination-free, and scalable paradigm for autonomous discovery of new physics.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28935
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Autonomous Discovery of Particle Physics Theories from Experimental Data
Alexander, Stephon
Bradley, Benjamin
Gouskos, Loukas
Niu, Cooper
High Energy Physics - Phenomenology
High Energy Physics - Experiment
High Energy Physics - Theory
The search for physics beyond the Standard Model is hindered by a combinatorial explosion of possible theories. We introduce \textsc{Albert}, a neuro-symbolic artificial intelligence framework to systematically navigate this vast theory space. By encoding particle physics as a formal language, \textsc{Albert} generates tokenized sequences representing symmetries, particles, and interactions under a rule-based grammar, eliminating the hallucinations common in large language models. The reinforcement learning environment enforces first-principle theoretical constraints, computes observables with radiative corrections, and evaluates statistical likelihood via $χ^2$ analysis against experimental data. As a proof of concept, we train a 25-million-parameter transformer model using only legacy data from the Large Electron-Positron Collider, which contains no direct evidence of the top quark. Remarkably, \textsc{Albert} successfully rediscovered the Standard Model and autonomously inferred necessity and properties of the top quark, predicting its mass at $178.9\pm 5.0~\text{GeV}$, consistent with its modern measurement at the Large Hadron Collider. These results demonstrate the potential of AI-driven theory exploration as a rigorous, hallucination-free, and scalable paradigm for autonomous discovery of new physics.
title Autonomous Discovery of Particle Physics Theories from Experimental Data
topic High Energy Physics - Phenomenology
High Energy Physics - Experiment
High Energy Physics - Theory
url https://arxiv.org/abs/2603.28935