AI identifies new particle models that may explain neutrinos' tiny mass

AI system helps explain why neutrinos have mass — Diagram illustrating the reinforcement learning agent, AMBer. AMBer searches the space of models, taking actions to modify the model. Each model is then evaluated using a pipeline of physics software, which produces a reward depending on the χ2 of the fit to data and the number of model parameters. The reward and model inform the agent’s selection of the next action. This structure could be generalized to any model-building task by defining the space of models, providing the agent with the physics software necessary to calculate predictions, and designing a reward parameterizing the user’s preferences for output models. The result of this learning process is a set of models matching those preferences, which a physicist can use as a basis for further study. Credit: *Communications Physics* (2026). DOI: 10.1038/s42005-026-02627-2

Physicists at the University of California, Irvine, have developed an artificial intelligence system that can autonomously design theoretical physics models, a task traditionally carried out by human theorists. The approach allows researchers to explore large, uncharted areas of particle physics theory, helping identify promising new explanations for the behavior of neutrinos.

The system is called Autonomous Model Builder (AMBer), and was developed by a research team led by UC Irvine doctoral candidates Victoria Knapp-Pérez and Jake Rudolph in the Department of Physics and Astronomy. The work is published in Communications Physics.

AMBer uses reinforcement learning, a form of artificial intelligence that learns through trial and error rather than by following predefined instructions. As it explores possible particle physics theories, the system evaluates its own choices and improves over time.

"Reinforcement learning is different from other kinds of machine learning, in which models predict labels or find patterns in data," Rudolph said. "AMBer's RL framework allows it to learn about the space of theoretical models as it explores, effectively creating its own training data as it searches for promising models."

How the system builds theories

The system constructs particle physics models by selecting mathematical symmetry groups, determining which particles to include, and assigning how those particles behave under the chosen symmetries. Each proposed model is evaluated based on how well it matches experimental data while minimizing the number of adjustable parameters, a key measure of a theory's predictive power.

The researchers tested AMBer on well-studied classes of neutrino theories and demonstrated that it could reproduce known results. They then applied the system to previously unexplored mathematical frameworks, identifying new candidate models that may merit further investigation.

Neutrino mass remains unresolved

Neutrinos are subatomic particles with an extremely small but nonzero mass, a property not explained by the Standard Model of particle physics. Developing theories that explain neutrino mass remains one of the field's major challenges.

The researchers emphasized that the system is designed to assist—not replace—human physicists by narrowing vast theoretical spaces down to the most promising candidates.

"AMBer functions as a filter, giving human physicists a better-informed starting point from which to study more complex behavior of neutrino models," Knapp-Pérez said.

Publication details

Jason Benjamin Baretz et al, Towards AI-assisted neutrino flavor theory design, Communications Physics (2026). DOI: 10.1038/s42005-026-02627-2

Who's behind this story?

Stephanie Baum

Master's in TESOL from The New School. Passionate about language learning and editing science news on biology and space exploration. Full profile →

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: AI identifies new particle models that may explain neutrinos' tiny mass (2026, July 9) retrieved 12 July 2026 from https://phys.org/news/2026-07-ai-particle-neutrinos-tiny-mass.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.