Reseña de «Ax-Prover: A deep reasoning agentic framework for theorem p

En el artículo «Ax-Prover: A deep reasoning agentic framework for theorem proving in mathematics and quantum physics» se presenta Ax-Prover, un sistema que combina modelos de lenguaje generales con el

Reseña de «Gauss – towards autoformalization for the working mathemati

En la conferencia «Gauss – towards autoformalization for the working mathematician», Jared Duker Lichtman presentó el proyecto Gauss, que busca automatizar la traducción de pruebas matemáticas a códig

Reseña de «¿Cuándo podrá la Inteligencia artificial ayudarnos a demost

En la conferencia «¿Cuándo podrá la Inteligencia artificial ayudarnos a demostrar teoremas?» se explica que la IA ya ayuda, pero con límites. Actualmente, es experta en reconocer patrones para encontr

Readings shared April 4, 2026

The readings shared in Bluesky on 4 April 2026 are: Why Lean?. ~ Leonardo de Moura. #LeanProver #ITP A formalization of the Gelfond-Schneider theorem. ~ Michail Karatarakis, Freek Wiedijk. #LeanProve

How effective are current AI models on mathematical research problems? « Math Scholar

Short proofs in combinatorics and number theory

We give a triplet of short proofs, each of which answers a question raised by Erdős. The first concerns the small prime factors of $\binom{n}{k}$, the second concerns whether an additive basis $A$ can always be split into pieces $A_1$ and $A_2$ such that each of $A_i + A_i$ has bounded gaps, and the final concerns whether $\{αp\}$ is "well-distributed" in the sense introduced by Hlawka and Petersen. In each case, the proof is due entirely to an internal model at OpenAI.

This startup wants to change how mathematicians do math

Axiom Math is giving away a powerful new AI tool. But it remains to be seen if it speeds up research as much as the company hopes.

Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP

We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant, autonomously proved 10 of 12 problems from the 2025 Putnam Mathematical Competition. The MCP tools, designed with Claude by analyzing logs from a prior experiment on miniF2F-Rocq, encode a "compile-first, interactive-fallback" strategy. Running on an isolated VM with no internet access, the agent deployed 141 subagents over 17.7 hours of active compute (51.6h wall-clock), consuming approximately 1.9 billion tokens. All proofs are publicly available.

Optimal bounds for an Erdős problem on matching integers to distinct multiples

Let $f(m)$ be the largest integer such that for every set $A = \{a_1 < \cdots < a_m\}$ of $m$ positive integers and every open interval $I$ of length $2a_m$, there exist at least $f(m)$ disjoint pairs $(a, b)$ with $a \in A$ dividing $b \in I$. Solving a problem of Erdős, we determine $f(m)$ exactly, and show $$ f(m)=\min\bigl(m,\lceil 2\sqrt{m}\,\rceil\bigr) $$ for all $m$. The proof was obtained through an AI-assisted workflow: the proof strategy was first proposed by ChatGPT, and the detailed argument was subsequently made fully rigorous and formally verified in Lean by Aristotle. The exposition and final proofs presented here are entirely human-written. [This paper solves Problem #650 on Bloom's website "Erdős problems".]

Reseña de «The story of Erdős problem #1026»

En el artículo «The story of Erdős problem #1026», Terence Tao detalla la resolución de un problema de 1975 mediante una colaboración híbrida entre matemáticos y herramientas de IA. El proceso incluyó