Back to #software testing

Neuro-Formal Verification: Agentic Language-Agnostic Formal Program Reasoning

Aug 2026 · 0 citations · 60 references
Computer Science

TL;DR

Neuro-formal verification is introduced, which harnesses that automation for developers of mainstream programming languages and returns a Dafny proof of correctness or of a bug on 57% of the entries at 92% precision, and a CBMC counterexample for 63% of the buggy programs at 90% precision.

Abstract

Formal verification offers the strongest assurance available for software, and verification-aware languages have made its automation real. Yet the benefits reach few mainstream developers, most of whose languages have no verification support. Besides, specifying properties and modeling the environment require expertise in formal methods. Proof is therefore reserved for a few celebrated artifacts, while the production code that ships is attested only through review and testing. We introduce neuro-formal verification (NFV), which harnesses that automation for developers of mainstream programming languages: an AI coding agent translates, an established verifier decides, and a question posed in a mainstream language is answered push-button, at empirical accuracy rather than soundness, with a machine-checked proof. Results on a dataset of correct and incorrect solutions to Python programming problems are encouraging: NFV returns a Dafny proof of correctness or of a bug on 57% of the entries at 92% precision, and a CBMC counterexample for 63% of the buggy programs at 90% precision.

View source

Similar papers

#software testing Preprint Aug 2026

SweepLSD: A One-Pass, O(width)-Memory Line Segment Detector with an Integer-Only Streaming Core and a Real-Time FPGA Realization

The first complete description of SweepLSD is given, a line segment detector that reads the image exactly once and emits each segment within a few rows of its last pixel passing the scan line, with the tightest frame-time distribution and the best per-segment direction accuracy of the four detectors.

Yoshiyasu Shimizu · 0 citations
#software testing Review Aug 2026

ChatGPT Solves All Tested Qiskit Homework Assignments

This study examined whether introductory Qiskit homework could remain autogradable while requiring students to run, review, and discuss results rather than banning AI.

A. Kaltchenko, Gurnivaj Tiwana · 0 citations

Mixed Reality Glasses Image Translocation for Binocular Diplopia.

This prototype MRG image translocation software was helpful to 69% of patients with binocular diplopia, but limited by large angle strabismus because of the limited instrument field of view.

Edsel B Ing, Kevin Sha, Sarosh Dandoti et al. · 0 citations
#software testing Open access Aug 2026

Multi-Disease Prediction Using Machine Learning: A Web-Based Diagnostic Support System for Diabetes, Heart Disease, and Parkinson\'s Disease

A diagnostic support system based on a unified web platform that classifies patients according to the risks of developing three diseases based on regularly collected clinical or audio data using classical supervised learning algorithms is presented.

Vedamurthy D R, Dr. Anup Ritti, A. Bibi et al. · 0 citations
#software testing Review Aug 2026

The Influence of Green Procurement on Supply Chain Resilience in Nigeria Maritime University, South-South Region

A high initial investment in acquiring environmentally friendly products can discourage institutions from adopting them. This study explored the extent to which eco-friendly products contribute to supply chain resilience and operational performance at the Nigerian Maritime University. The study employed a quantitative survey method administering a sample of 303copies questionnaire to the staff of the organization using a stratified sampling technique. The hypotheses were tested and analyzed using a regression method with the aid of Minitab software. The regression analysis indicates eco-friendly products significantly relates to operational efficiency in Nigerian Maritime University, South-South Nigeria. The model regression indicates (R² = 99.20, B = 1.039, β = 0.0162, p = 0.000); indicating that the model is a good fit. The coefficient 1.0399 is highly significant (p < 0.001). This indicates a positive and strong effect, explaining that for every one-unit increase in eco-friendly products, the operational efficiency increases by approximately 1.039 units. The NOVA result confirms F = 4117.07, p < 0.001. The study concludes that the adoption of eco-friendly products plays a significant and positive role in enhancing organizational sustainability performance or resilience. Organizations should embed eco-friendly product selection into their procurement guidelines to promote sustainable operations. Management should invest in environmentally friendly technologies and capacity building initiatives to support the transition to sustainable practices.

Ikenna Christopher Ugwu · 0 citations

Related blog posts

MIT News · Artificial Intelligence Aug 17, 2026

Q&A: Rethinking how innovation happens

In his latest book, Professor Eugene Fitzgerald examines the forces that turn breakthroughs into value — and why innovation resists simple formulas.