Solver Agent: an Agentic AI Framework for Theoretical Physics Computations Applied to F-theory Uplifts of O3-planes and S-folds
Authors: Eliott Morgensztern, Cesar Fierro Cota, Alessandro Mininno
Organizations: Sorbonne Université, CNRS, Laboratoire de Physique Théorique et Hautes Energies, Campus Pierre et Marie Curie, 4 place Jussieu, F-75005, Paris, France · Department of Physics, University of Wisconsin–Madison, 1150 University Avenue, Madison, WI 53706, USA
We introduce Solver Agent, an AI framework based on large language models for calculations and proofs in mathematics and theoretical physics. The solution process is tracked through a persistent ledger that records assumptions, derivations, and computations. A central agent delegates tasks to specialized sub-agents, while independent agents verify both intermediate steps and the final result. This setup improves the traceability, reproducibility, and verification of computer-assisted calculations. Applying Solver Agent, we study global F-theory uplifts of Type IIB orientifolds and their S-fold generalizations. We establish sufficient conditions for Weierstrass models over projective threefolds with terminal Zk quotient singularities (k∈{2,3,4,6}) to give Q-factorial projective elliptically fibered Calabi-Yau fourfolds with isolated Gorenstein terminal quotient singularities. These geometries realize O3-planes and S-folds, where local D3-brane probes of the latter yield four-dimensional N=3 superconformal field theories. Using stringy invariants, we derive fixed-point contributions to Hodge data and Euler characteristics, and show that these Euler corrections determine the localized D3-brane charges required for tadpole cancellation. We illustrate these results using toric hypersurface constructions, where a single three-dimensional polytope determines both the Type IIB Calabi-Yau threefold and the F-theory base; here, the orientifold double cover naturally forms a bisection of an alternative genus-one-fibered uplift with discrete Z2 gauge symmetry. Finally, we provide methods for toric computations and four-form flux analysis in four-dimensional N=1 compactifications with non-abelian gauge sectors.
Figures & tables
Section
Purpose
Prompt
Result
Section 4.1
Check terminal singularities
4.1
4.1
Count terminal singularities
4.1
4.1
Identify local groups
4.1
4.1
Section 4.2
Prove Theorem 4.2
4.2
4.2
Section 4.3
Stringy Euler definition
4.3
4.3
Compute stringy Euler
4.3
4.3
Table 1 : Overview of prompts provided to Solver Agent and their corresponding results, categorized by section and purpose.
Entry type
Written by
Content
Assumption
main solver
interpretive choices, definitions, notation, conventions, domains of validity
Derivation
main solver
reasoning steps and plans, in mathematical prose
Result
main solver
interpretation of a computation, with an explicit dependence on it
Symbolic computation
sub-agent
computer-algebra task, code, and output
Numerical computation
sub-agent
numerical task, code, output, and generated files
Calabi–Yau analysis
sub-agent
geometric quantities from domain-specific software
Table 2 : Entry types of the solution ledger. Each entry carries a status (accepted, rejected, or superseded), a summary, a detailed body, and references to the entries on which it depends.
X3
B3
κ
c2(TX3)⋅J
χ(X3)
nsing(B3)
X8
P3
2
44
−296
0
X10
P[1,1,1,2]3
1
34
−288
1
Table 3 : Here J is the Kähler class in X3 , κ=∫XJ3 , and nsing(B3) is the number of terminal quotient singularities associated to the base B3 of a given F-theory uplift for X3 .