ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
Researchers have developed ImProver 2, a neurosymbolic framework designed to optimize formal mathematical proofs within the Lean 4 environment. This system employs an expert-iteration pipeline and a scaffold that integrates formal structure with informal abstractions to address challenges like heterogeneous objectives and high computational costs. A 7B-parameter model trained with ImProver 2 has demonstrated performance competitive with larger frontier models and significantly improved efficiency across various metrics, suggesting proof optimization is a scalable and learnable task. AI
IMPACT Demonstrates that smaller AI models, when properly trained and scaffolded, can effectively restructure complex research-level proofs, potentially making formal mathematics more accessible.