Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization

• URL: http://arxiv.org/abs/2604.16347v1
• Date: Mon, 16 Mar 2026 14:19:33 GMT
• Title: Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization
• Abstract summary: We propose a human-in-the-loop approach in which human scientists and AI collaboratively produce formal proofs.<n>We develop Lean Atlas, a Lean 4 tool that visualizes the dependency graph of a Lean 4 project as an interactive web viewer.<n>Core feature, Lean Compass, is an algorithm that, given a selected theorem set, automatically extracts the project-specific nodes.
• Score: 1.711666249985278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-driven autoformalization of mathematics is advancing rapidly. However, the type checker of a proof assistant guarantees only the logical correctness of proofs; it does not verify whether propositions and definitions faithfully capture their intended mathematical content. Consequently, AI-generated formal proofs can exhibit semantic hallucination-passing the type checker yet failing to express the intended mathematics. We propose a human-in-the-loop approach in which human scientists and AI collaboratively produce formal proofs, with humans responsible for the semantic verification of propositions and definitions. To realize this approach, we develop Lean Atlas, a Lean 4 tool that visualizes the dependency graph of a Lean 4 project as an interactive web viewer, enabling human scientists to grasp the overall structure of a formalization efficiently. Its core feature, Lean Compass, is an algorithm that, given a selected theorem set, automatically extracts the project-specific nodes whose semantic correctness can affect those target statements, thereby reducing the candidate set for semantic review in large-scale formalizations. We further define *aligned Lean code* as formalization code that has undergone human semantic verification, and propose it as a quality standard for AI-generated formalizations. We evaluate the tool on six Lean 4 formalization projects with different structural characteristics; proof-heavy projects (PrimeNumberTheoremAnd, Carleson, Brownian Motion) achieved 94-99% average node reduction, a 6-theorem milestone subset of FLT achieved 59.8%, mixed PhysLib 69.0%, and definition-heavy XMSS 27.3%. Lean Atlas is available as open-source software at https://github.com/NyxFoundation/lean-atlas .

Related papers

• AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics [0.0]
  AxQM is the largest proof-synthesis benchmark in physics by a factor of four.<n>By task count, it is the largest proof-synthesis benchmark in physics by a factor of four.
  arXiv  Detail & Related papers  (2026-09-04T13:58:19Z)
• MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research [62.221184989046826]
  MathCoPilot is a human-in-the-loop system that embodies a new human--AI symbiotic paradigm for mathematical research.<n>MathCoPilot unifies three core capabilities: an interactive proof blueprint that decomposes a proof into navigable steps the human can directly inspect, direct, and refine; automated proving skill orchestration with adaptive knowledge base search and Lean-integrated iterative verification; and topic-driven paper retrieval and automated formalization into a verified Lean knowledge base.
  arXiv  Detail & Related papers  (2026-07-16T05:22:40Z)
• Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics [20.90238876313568]
  Large Language Models (LLMs) produce subtle errors that evade human detection.<n>Recent trends indicate that general-purpose LLMs now outperform smaller models explicitly fine-tuned for Lean.<n>We introduce an agentic autoformalization framework powered by general coding LLMs.
  arXiv  Detail & Related papers  (2026-06-30T05:05:03Z)
• Benchmarking Testing in Automated Theorem Proving [39.65133452374143]
  T is a framework that evaluates the semantic correctness of formal theorems.<n>We construct a benchmark from 5 real-world Lean 4 repositories.<n>Experiments demonstrate that while state-of-the-art models achieve high compilation success, they perform significantly worse under our semantic metric.
  arXiv  Detail & Related papers  (2026-04-26T13:24:20Z)
• Evaluating Frontier LLMs on PhD-Level Mathematical Reasoning: A Benchmark on a Textbook in Theoretical Computer Science about Randomized Algorithms [14.853721511192736]
  Large language models (LLMs) have led to breakthroughs in automated mathematical reasoning and scientific discovery.<n>We present a benchmark of four frontier models: GP-5-Thinking, Gemini-3-Pro, Claude-Sonnet-4.5-Thinking, and Grok-4.<n>We find that while the top-tier models achieve a high accuracy rate, other models lag significantly in consistency.
  arXiv  Detail & Related papers  (2025-12-16T00:34:55Z)
• BRIDGE: Building Representations In Domain Guided Program Verification [67.36686119518441]
  BRIDGE decomposes verification into three interconnected domains: Code, Specifications, and Proofs.<n>We show that this approach substantially improves both accuracy and efficiency beyond standard error feedback methods.
  arXiv  Detail & Related papers  (2025-11-26T06:39:19Z)
• Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph [7.606625807305093]
  We present Aria, a system for conjecture-level formalization in Lean.<n>Aria emulates human expert reasoning via a two-phase Graph-of-Thought process.<n>AriaScorer retrieves definitions from Mathlib for term-level grounding.
  arXiv  Detail & Related papers  (2025-10-06T06:25:11Z)
• Solving Inequality Proofs with Large Language Models [42.667163027148916]
  Inequality proving is crucial across diverse scientific and mathematical fields.<n>This makes it a demanding frontier for large language models (LLMs)<n>We release IneqMath, an expert-curated dataset of Olympiad-level inequalities.
  arXiv  Detail & Related papers  (2025-06-09T16:43:38Z)
• Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification [56.218970738892764]
  Chain-of-Thought prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs)<n>To mitigate hallucinations in CoT that are notoriously difficult to detect, current methods operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness.<n>We propose a retrospective, step-aware formal verification framework $Safe$. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations.
  arXiv  Detail & Related papers  (2025-06-05T03:16:08Z)
• LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction [74.79306773878955]
  We introduce LeanProgress, a method that predicts the progress in the proof.<n>Our experiments show that LeanProgress achieves an overall prediction accuracy of 75.1%.
  arXiv  Detail & Related papers  (2025-02-25T07:46:36Z)
• Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation [71.32761934724867]
  This work proposes Alchemy, a framework for data synthesis that constructs formal theorems through symbolic mutation.<n>For each candidate theorem in Mathlib, we identify all invocable theorems that can be used to rewrite or apply to it.<n>As a result, our method increases the number of theorems in Mathlib by an order of magnitude, from 110k to 6M.
  arXiv  Detail & Related papers  (2024-10-21T08:04:21Z)
• DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data [65.5290035371111]
  We introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. We fine-tune the DeepSeekMath 7B model on this synthetic dataset, which comprises 8 million formal statements with proofs. Our model successfully proved 5 out of 148 problems in the Lean 4 Formalized International Mathematical Olympiad (FIMO) benchmark, while GPT-4 failed to prove any.
  arXiv  Detail & Related papers  (2024-05-23T09:03:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.