LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification

The paper introduces DynaCertBench, a benchmark of 105 diverse systems for certifying stability, safety, and related properties, and presents LLM2Cert, a framework that uses large language models to generate and verify candidate certificates via SMT solvers or Lean. LLM2Cert achieves a 77.1% verification rate on the benchmark, improving by 17.1 percentage points over a single-shot approach, and successfully verifies 22 certificates that All-SMT could not resolve. The authors provide code and data on GitHub for reproducibility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• agents
• benchmarks
• safety