Work

The FERMIACC: Agents for Particle Theory

Year: 2026

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2603.22538

Authors: Agrawal, Prateek, Craig, Nathaniel, Madden, Amalia, Lombera, Iñigo Valenzuela

Institutions: University of California, Santa Barbara, Kavli Institute for Theoretical Physics

Topic: Particle physics theoretical and experimental studies

Subfield: Nuclear and High Energy Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Gordon and Betty Moore Foundation, China Scholarship Council, University of California, Santa Barbara, Materials Research Science and Engineering Center, Harvard University, Division of Materials Research, California NanoSystems Institute

Awards: G1110399006, G1141670404, G2232042528, G2500807902, G2760720504, Materials Research Science and Engineering Center at UCSB, G3349485200, G3400352658, G401861217, G4281768896, Postdoctoral Fellows Support at KITP, Kavli Institute for Theoretical Physics, MRI: Acquisition of a High Performance Central Computing Facility at University of California Santa Barbara

OpenAlex ID: W7140340298

Cites:

Cited by:

Related to: