Researchers introduced MAGS, a unified multi-agent framework that generates executable programs with formal safety guarantees by using Dafny as a verification-aware intermediate representation, accord…
A comparison of four formal-verification tools — Bend, Verus, Dafny and Lean — argues that proofs, not tests, are what make agent-written code trustworthy, citing Amazon Science's August 31, 2026 post…
A paper submitted to arXiv on 21 Aug 2026 and revised 14 Sep 2026 introduces neuro-formal verification (NFV), a method in which an AI coding agent formalizes source-level verification problems into pr…
A developer working on the Beneficial AI Foundation's vericoding benchmark questions whether the open-weight models GLM-4.5 and DeepSeek V3.1 were run with their thinking modes enabled, noting that th…
A new open-source framework called Agent Control Plane (ACP) moves AI agent authorization outside the model, into a structured-input control plane where prompt injection cannot reach, ensuring a compr…
Researchers introduced Vero, the first benchmark to evaluate joint implementation and proof synthesis at the repository level, containing 43 multi-module instances from real-world repositories in Pyth…
AxDafny, a verifier-guided framework, achieved a 92.7% verification success rate on DafnyBench, outperforming GPT-5.5 by 6.5 percentage points. The tool generates code with proof artifacts, setting a …