AI RESEARCH
Agentic Proving for Program Verification
arXiv CS.AI
•
ArXi:2605.23772v1 Announce Type: new Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving framework on CLEVER, a Lean 4 benchmark for verifiable code generation.