LLM2Cert: LLM agents + Lean formally verify safety certificates for 77% of benchmark systems
wellecks · x · 2026-10-27
LLM2Cert, co-led by @Zhipeng0727 and @psong1, is billed as the first end-to-end framework bringing Lean theorem proving into agentic synthesis and verification of Lyapunov/barrier certificates for dynamical systems.
- Automatically synthesized and formally verified safety/stability certificates for 81 of 105 benchmark dynamical systems (77%)
- On a common subset, 2.1× the successes of 5 prior pipelines combined
- More details in the author's follow-up thread
Related event: LLM2Cert: LLM-Generated Safety Certificates with Automated Verification(2 posts)→
More from Research
- UC Berkeley paper: RL reweights LLM reasoning strategies rather than expanding them — burny_tech · 2026-10-27
- Dehaene lab finds a cortical map integrating integers and fractions via 7T fMRI — burny_tech · 2026-10-27
- LLM rewrites a physics paper into a clearer 12-page explainer — correctness unverified — thomasahle · 2026-10-27
- OpenAI's new math results accused of scooping community mathematician's Yang-Mills work — burny_tech · 2026-10-27
- NYC Reliable AI Meetup on Synthetic Data Set for Nov 16 with NYU's Gautam Kamath — karen_ullrich · 2026-10-27
- Meta's InteractiveWorld Benchmark Shows MLLMs Still Far from Reliable Physical Assistants — meta · 2026-10-27