A symbolic Lean 4 pipeline called LeanPolish released 33,402 accepted local edits and 65,596 same-state failed attempts to study what language models learn from verified proof-edit supervision, accord…
Mistral's Leanstral 1.5, an AI model designed to write formal mathematical proofs, unexpectedly discovered five previously unreported software bugs in open-source codebases by using its proof-checking…
Mistral AI released Leanstral 1.5, an open-source model for formal verification in Lean 4, achieving 100% on the miniF2F math benchmark and solving 587 of 672 Putnam problems. The model also caught fi…
Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers major performance upgrades in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems, and ach…
Mistral AI released Leanstral 1.5, an Apache-2.0 licensed Lean 4 code agent model that solves 587 of 672 PutnamBench problems. The model achieves state-of-the-art results on multiple theorem-proving b…
Researchers introduced VERITAS, a zero-shot framework for formal theorem proving that leverages rich verifier signals through a two-phase protocol combining Best-of-N sampling and critic-guided Monte …
Researchers at UC Riverside introduced the first robustness study for proof autoformalization in Lean 4, testing seven LLM-based models on perturbed informal proofs. All models showed sensitivity to g…