math.AGMay 24, 2026

Positivity in classical enumerative geometry: a case study in synchronized AI-assisted mathematics

Authors: Gergely BércziLászló M. Fehér

Abstract

We study the symmetric polynomial αAn,d(1+α1x1++αnxn)\prod_{α\in A_{n,d}}\bigl(1+α_1 x_1+\cdots+α_n x_n\bigr) where An,d:={αZ0n:α=d}A_{n,d}:=\{α\in\mathbb{Z}_{\ge 0}^n:|α|=d\}, which is the total Chern class of Symd(Cn)\mathrm{Sym}^d(\mathbb{C}^n), viewed as a torus representation whose Chern roots are the weights α1x1++αnxnα_1 x_1+\cdots+α_n x_n for αAn,dα\in A_{n,d}. Its homogeneous degree-kk part ck(n,d)c_k(n,d) is the kk-th Chern class of Symd(Cn)\mathrm{Sym}^d(\mathbb{C}^n). These Chern classes, together with their coefficients in various symmetric function bases, play a central role in enumerative geometry. Despite their simple definition, general closed formulas for their coefficients are subtle, and many structural properties of these classes have remained poorly understood. In this paper we prove several conjectures concerning their structure, establish explicit formulas, and study log-concavity properties for both the Chern classes and their KK-theoretic analogue. In rank two, passing to the Schur basis and expanding the Schur coefficients in the binomial basis of dd, we uncover a new binomial log-concavity phenomenon and prove refined positivity results. The paper demonstrates a novel methodology: we combine several AI systems with human mathematical insight in a coordinated workflow, deploying each tool according to its strengths in experimental discovery, conjecture formation, symbolic proof construction, and verification. To our knowledge, this is one of the first detailed case studies of orchestrating multiple AI tools to make substantial progress on a coherent mathematical research project.

Explore similar work

Aug 11, 2026cs.AI

Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration

AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant KGK_G, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of KGK_G is not known, we recently tightened the best known bounds to 6π11    KG    π2log(1+2)104.\frac{6π}{11} \;\le\; K_G \;\le\; \fracπ{2\log(1+\sqrt2)} - 10^{-4}. Crucially, these improvements were achieved using an AI research system that could arrive at insights deemed novel by domain experts. We give a detailed discussion of our experience using AI for mathematics research, particularly touching upon its strengths and weaknesses, as well as our experience with creating ideal conditions for AI to arrive at breakthrough insights.
Alan Li, Rahul Saha, Anton Xue +4
May 27, 2026math.AG

Real-rootedness of the Poincaré polynomials of \overline{\mathcal M}_{0,n}: an AI-assisted proof

We prove real-rootedness for the Poincaré polynomial Pn(t)=i=0n3dimH2i(M0,n;Q)tiP_n(t)=\sum_{i=0}^{n-3} \dim H^{2i}(\overline{\mathcal M}_{0,n};\mathbb{Q})t^i of the Deligne--Mumford moduli space M0,n\overline{\mathcal M}_{0,n} of stable nn-pointed rational curves, proving a conjecture of Aluffi--Chen--Marcolli. The proof starts from the Keel--Manin--Getzler recurrence, but its main new idea is a bivariate deformation Fm(y,t)F_m(y,t) of the Poincaré polynomial. This deformation reveals a hidden interlacing structure not visible in the one-variable recurrence. For fixed t<0t<0, the zero set of FmF_m in the yy-direction is controlled by a Sturm--Rolle argument on the interval 0<y<1t0<y<1-t. The original polynomial is recovered on the slice y=1y=1, and the ordered crossings of the moving roots through this slice give both real-rootedness and strict interlacing. Consequently, the Betti numbers of M0,n\overline{\mathcal M}_{0,n} form an ultra-log-concave sequence. We further prove real-rootedness and ultra-log-concavity for the Poincaré polynomial of the Fulton--MacPherson space P1[n]\mathbb{P}^1[n] of nn ordered points in degenerations of the complex projective line. The proof for M0,n\overline{\mathcal M}_{0,n} was obtained through an iterative AI-assisted workflow with Co-Mathematician, an agentic frontier-model system developed by Google DeepMind. Our role was to formulate the problem, evaluate the proposed proof attempts, identify gaps and request corrections, compare the developing argument with the literature, and refine the presentation of the final proof. Our additional human contribution was to observe that a similar residual deformation strategy applies to the Fulton--MacPherson spaces P1[n]\mathbb P^1[n], yielding the corresponding real-rootedness theorem.
Gergely Bérczi, Young-Hoon Kiem
May 7, 2026cs.AI

AI co-mathematician: Accelerating mathematicians with agentic AI

We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.
Daniel Zheng, Ingrid von Glehn, Yori Zwols +15