https://doi.org/10.1140/epjc/s10052-025-14707-8
Review
Large physics models: towards a collaborative approach with large language models and foundation models
1
CLPS-Centre for Logic and Philosophy of Science, UGent, Ghent, Belgium
2
IMAPP, Radboud University and Nikhef, Nijmegen, The Netherlands
3
Utrecht University, Utrecht, The Netherlands
4
Institute for Science in Society, Radboud University, Nijmegen, The Netherlands
5
Instituto de Física Corpuscular (IFIC), CSIC-UV, Valencia, Spain
6
University of Twente, Enschede, The Netherlands
7
TU Dresden & ScaDS.AI, Dresden/Leipzig, Germany
8
ErUM-Data-Hub & TU Dortmund University, Dortmund, Germany
9
University of Geneva, Geneva, Switzerland
10
Munich Center for Mathematical Philosophy, LMU Munich, Munich, Germany
11
Computing and Information Science, Radboud University, Nijmegen, The Netherlands
12
Physics Department, TUM School of Natural Sciences, Technical University of Munich, Munich, Germany
13
TU Wien, Vienna, Austria
14
Thapar Institute of Engineering and Technology (TIET), Patiala, India
15
Universität Hamburg, Hamburg, Germany
16
Institute of Philosophy and Sociology at Polish Academy of Sciences, Warsaw, Poland
17
Department of Theoretical Philosophy at University of Groningen, Groningen, The Netherlands
18
RWTH Aachen University, Aachen, Germany
19
Institute of Physics of Cantabria (IFCA), CSIC-UC, Santander, Spain
20
Ippen Digital, Munich, Germany
21
Universidad de Oviedo and ICTEA, Oviedo, Spain
22
GRAPPA, Institute of Physics, University of Amsterdam, Amsterdam, The Netherlands
Received:
1
May
2025
Accepted:
1
September
2025
Published online:
25
September
2025
This paper explores the development and evaluation of physics-specific large-scale AI models, which we refer to as large physics models (LPMs). These models, based on foundation models such as large language models (LLMs) are tailored to address the unique demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing insights from physical theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection. Development focuses on constructing models capable of processing physics texts, mathematical formulations, and diverse physical data. Evaluation assesses accuracy and reliability through testing and benchmarking. Finally, Philosophical Reflection encompasses the analysis of broader implications of LLMs in physics, including their potential to generate new scientific understanding and what novel collaboration dynamics might arise in research. Inspired by the organizational structure of experimental collaborations in particle physics, we propose a similarly interdisciplinary and collaborative approach to building and refining large physics models. This roadmap provides specific objectives, defines pathways to achieve them, and identifies challenges that must be addressed to realise physics-specific large scale AI models.
© The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Funded by SCOAP3.
