LeanArchitect: Automating Blueprint Generation for Humans and AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Thomas, Monticone, Pietro, Avigad, Jeremy, Welleck, Sean
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914293453160448
author Zhu, Thomas
Monticone, Pietro
Avigad, Jeremy
Welleck, Sean
author_facet Zhu, Thomas
Monticone, Pietro
Avigad, Jeremy
Welleck, Sean
contents Large-scale formalization projects in Lean rely on blueprints: structured dependency graphs linking informal mathematical exposition to formal declarations. While blueprints are central to human collaboration, existing tooling treats the informal ($\LaTeX$) and formal (Lean) components as largely decoupled artifacts, leading to maintenance overhead and limiting integration with AI automation. We present LeanArchitect, a Lean package for extracting, managing, and exporting blueprint data directly from Lean code. LeanArchitect introduces a declarative annotation mechanism that associates formal declarations with blueprint metadata, automatically infers dependency information, and generates $\LaTeX$ blueprint content synchronized with the Lean development. This design eliminates duplication between formal and informal representations and eases fine-grained progress tracking for both human contributors and AI-based theorem provers. We demonstrate the practicality of LeanArchitect through the automated conversion of several large existing blueprint-driven projects, and through a human--AI collaboration case study formalizing a multivariate Taylor theorem. Our results show that LeanArchitect improves maintainability, exposes latent inconsistencies in existing blueprints, and provides an effective interface for integrating AI tools into real-world formalization workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22554
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LeanArchitect: Automating Blueprint Generation for Humans and AI
Zhu, Thomas
Monticone, Pietro
Avigad, Jeremy
Welleck, Sean
Logic in Computer Science
Large-scale formalization projects in Lean rely on blueprints: structured dependency graphs linking informal mathematical exposition to formal declarations. While blueprints are central to human collaboration, existing tooling treats the informal ($\LaTeX$) and formal (Lean) components as largely decoupled artifacts, leading to maintenance overhead and limiting integration with AI automation. We present LeanArchitect, a Lean package for extracting, managing, and exporting blueprint data directly from Lean code. LeanArchitect introduces a declarative annotation mechanism that associates formal declarations with blueprint metadata, automatically infers dependency information, and generates $\LaTeX$ blueprint content synchronized with the Lean development. This design eliminates duplication between formal and informal representations and eases fine-grained progress tracking for both human contributors and AI-based theorem provers. We demonstrate the practicality of LeanArchitect through the automated conversion of several large existing blueprint-driven projects, and through a human--AI collaboration case study formalizing a multivariate Taylor theorem. Our results show that LeanArchitect improves maintainability, exposes latent inconsistencies in existing blueprints, and provides an effective interface for integrating AI tools into real-world formalization workflows.
title LeanArchitect: Automating Blueprint Generation for Humans and AI
topic Logic in Computer Science
url https://arxiv.org/abs/2601.22554