arXiv:2606. 14000v1 Announce Type: new Abstract: Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance.
arXiv:2606. 26525v1 Announce Type: new Abstract: Auto-formalization is critical for scalable formal verification, but existing progress largely focuses on isolated statements, while theory-scale auto-formalization, which coherently translates hundreds of interdependent definitions, lemmas, and theorems, remains open due to challenges in consistency, faithfulness, scalability, and correctness.
arXiv:2606. 31134v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated exceptional capabilities in mathematical reasoning, they frequently produce subtle errors that evade human detection.
Magenta is a training‑free pipeline that bridges informal natural‑language mathematical problems and formal Lean 4 verification. Given a problem in plain text, it generates an answer, translates it into a Lean 4 statement, and constructs a machine‑checked proof. The system includes a statement judge to ensure the formalisation matches the original problem and an error‑attribution judge to guide corrections, achieving perfect accuracy on olympiad benchmarks and solving all six IMO 2026 problems when combined with K2‑Horizon‑7B.
arXiv:2606. 29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof.
arXiv:2606. 06523v1 Announce Type: new Abstract: Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence.
arXiv:2608. 14221v1 Announce Type: new Abstract: Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4.
arXiv:2605. 20531v2 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning.
ProofJudge is an agentic large language model that evaluates the quality of formal proofs in Lean 4 beyond mere correctness. It scores proofs on five dimensions—library leverage, automation fit, structural clarity, statement quality, and Mathlib conventions—using tool access to the relevant repository commit. The system was tested on 218 Mathlib declarations, achieving alignment with human reviewers between 63.5% and 80.8% and releasing its harness, dataset, and traces for open research.
arXiv:2606. 01008v1 Announce Type: cross Abstract: We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks.
FaithSieve is a Lean‑assisted framework that fine‑grains natural‑language mathematical proofs into local reasoning units, extracts typed proof obligations, and verifies them with formal evidence gated by semantic alignment. It introduces two expert‑verified datasets—ProofLoc‑Olympiad and ProofLoc‑University—to benchmark first‑error localization. On these benchmarks, FaithSieve outperforms direct‑judging baselines, achieving 81.43% and 84.5% exact first‑error accuracy respectively.
Formal proofs in Lean 4 that pass the kernel's type checker can nonetheless vary widely in quality. We introduce ProofJudge, an agentic LLM-as-judge system that scores formal proof quality along five...