English

The FERMIACC: Agents for Particle Theory

High Energy Physics - Phenomenology 2026-03-25 v1

Abstract

We present the FERMIACC, a scaffolded reasoning model built on OpenAI agents designed to autonomously generate and quantitatively validate theory hypotheses for high energy physics data at scale.

Cite

@article{arxiv.2603.22538,
  title  = {The FERMIACC: Agents for Particle Theory},
  author = {Prateek Agrawal and Nathaniel Craig and Amalia Madden and Iñigo Valenzuela Lombera},
  journal= {arXiv preprint arXiv:2603.22538},
  year   = {2026}
}

Comments

15 pages, 9 figure, 4 appendices

R2 v1 2026-07-01T11:34:24.519Z