RESEARCH

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

ArXiv cs.AI · Mon, 25 May 2026 04:00:00 GMT

arXiv:2605.22885v1 Announce Type: new Abstract: Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by

Read original source Discuss with A.S.I.S