Saved in:
Bibliographic Details
Main Authors: Rammal, Ahmad, Patel, Niket, Gloeckle, Fabian, Hayat, Amaury, Kempe, Julia, Munos, Remi, Arnal, Charles, Cabannes, Vivien
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29955
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of 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.