# Process-Verified Reinforcement Learning for Theorem Proving via Lean

Source: https://arxiv.org/abs/2606.20068
Published: 2026-06-18
Status: unreviewed source report

## Source excerpt (up to 25 words)

> While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained

## Review question

Inspect the formal statement, imported axioms, admitted lemmas, checker version and correspondence with the informal theorem. A successful compiler exit alone does not prove that the intended question was formalized.

No independent proof check or claim of peer review.