LeanArchitect: Automating Blueprint Generation for Humans and AI
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jan 2026.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2026: 6.
6 papers.
- 2026LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalizationcited by 12
- 2026Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinementcited by 9
- 2026BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprintscited by 2
- 2026CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inferencecited by 1
- 2026Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem Provingcited by 0
- 2026LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphscited by 0
- 2026LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs8 Oct 2026
- 2026BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprints30 Jul 2026
- 2026CausalSmith: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference24 Jul 2026
- 2026Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem Proving4 Jun 2026
- 2026Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement4 Jun 2026
- 2026LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization3 Jun 2026