Enregistré dans:
Détails bibliographiques
Auteurs principaux: Rammal, Ahmad, Patel, Niket, Gloeckle, Fabian, Hayat, Amaury, Kempe, Julia, Munos, Remi, Arnal, Charles, Cabannes, Vivien
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.29955
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911728441229312
author Rammal, Ahmad
Patel, Niket
Gloeckle, Fabian
Hayat, Amaury
Kempe, Julia
Munos, Remi
Arnal, Charles
Cabannes, Vivien
author_facet Rammal, Ahmad
Patel, Niket
Gloeckle, Fabian
Hayat, Amaury
Kempe, Julia
Munos, Remi
Arnal, Charles
Cabannes, Vivien
contents We present AutoformBot, a multi-agent system for building an Autoformalized Textbook Library At Scale (Atlas) in Lean 4. AutoformBot orchestrates thousands of LLM agents, equipped with formal verification tools, dependency-aware task scheduling, and collaborative version control, to translate informal textbook prose into machine-checked definitions and proofs. We apply our methods to a corpus of 26 open-access textbooks spanning analysis, algebra, topology, combinatorics, and probability, producing Atlas: a verified library of over 45,000 Lean 4 declarations and 500 thousand lines of code. We release two artifacts: (i) AutoformBot, the open-source multi-agent framework; and (ii) Atlas, the resulting formal library. Our results suggest that autoformalizing the core content of graduate-level mathematics at scale is now economically and technically feasible. This opens the door to the automated verification of both human- and machine-generated mathematics at a research level.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29955
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Formalizing Mathematics at Scale
Rammal, Ahmad
Patel, Niket
Gloeckle, Fabian
Hayat, Amaury
Kempe, Julia
Munos, Remi
Arnal, Charles
Cabannes, Vivien
Artificial Intelligence
We present AutoformBot, a multi-agent system for building an Autoformalized Textbook Library At Scale (Atlas) in Lean 4. AutoformBot orchestrates thousands of LLM agents, equipped with formal verification tools, dependency-aware task scheduling, and collaborative version control, to translate informal textbook prose into machine-checked definitions and proofs. We apply our methods to a corpus of 26 open-access textbooks spanning analysis, algebra, topology, combinatorics, and probability, producing Atlas: a verified library of over 45,000 Lean 4 declarations and 500 thousand lines of code. We release two artifacts: (i) AutoformBot, the open-source multi-agent framework; and (ii) Atlas, the resulting formal library. Our results suggest that autoformalizing the core content of graduate-level mathematics at scale is now economically and technically feasible. This opens the door to the automated verification of both human- and machine-generated mathematics at a research level.
title Formalizing Mathematics at Scale
topic Artificial Intelligence
url https://arxiv.org/abs/2605.29955