#Formal Verification

Governing LLM Reasoning with Formal Verification

EG-VAR introduces a Lean 4-based architecture for auditable LLM reasoning, achieving perfect accuracy and source fidelity on benchmarks by using formal verification as the sole claim issuer.

Erik Meijer: Making AI Provably Safe with Type Systems

Leibniz Labs' Erik Meijer explains how type systems and compiler knowledge can make AI agents provably safe, addressing the risks of tool use and infinite loops.

Mistral AI's Leanstral Tackles Trust in Code Generation

Mistral AI introduces Leanstral, an open-source code agent for Lean 4, aiming to bring formal verification to AI-generated code and boost engineering efficiency.

MLIPs: From Blind Screening to Certified Discovery

New framework Proof-Carrying Materials (PCM) ensures reliability for machine-learned interatomic potentials (MLIPs), dramatically improving materials discovery.

AlphaProof system proves its worth at the Math Olympiad