SOURCE-LINKED INTELLIGENCE

ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fully preserve this recursive structure, where the learning process should be self-improving over time. Existing methods either embed proof experience into model parameters through expensive weight updates, or keep verified intermediate deductions only within the current problem. In addition, these methods also heavily rely on sparse whole-proof feedback, even when unsuccessful partial attempts contain useful discoveries. To close the gap, we pro

Read original source ↗ Open in workspace

recordType

paper

region

Global