BeClaude
Research2026-05-06

Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification

Source: Arxiv CS.AI

arXiv:2604.17010v2 Announce Type: replace-cross Abstract: We introduce a self-play framework for semantic equivalence in Haskell, utilizing formal verification to guide adversarial training between a generator and an evaluator. The framework leverages Liquid Haskell proofs for validating...

arxivpapersreasoning