arXiv AI July 21, 2026 By Mansur Arief, Nur Ahmad Khatim, Ali Akarma, Ahmad Alfan Alfian Irfan

Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications

arXiv:2607. 17686v1 Announce Type: cross Abstract: Modern software teams have mature tools for low-level testing, such as pytest, JUnit, and Jest, which make it inexpensive to write unit tests and run them on every commit.

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 AI.

arXiv AI

Jul 21

Automated Hardware Validation Test Plan Generation for Large Scale AI Datacenter Platforms Using a Generative AI Multi-Agents Architecture

arXiv:2607. 16388v1 Announce Type: cross Abstract: Large-scale AI datacenter platforms comprise thousands of heterogeneous hardware components whose validation requires comprehensive fault injection test plans.

By Mohammed-Khalil Ghali, Saurabh Kulkarni, Prathamesh Kulkarni, Rohan Kulkarni, Sangwon Yoon, Daehan Won

agents

arXiv AI

Jun 2

FVSpec: Real-World Property-Based Tests as Lean Challenges

arXiv:2606. 01008v1 Announce Type: cross Abstract: We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks.

By Quinn Dougherty, Max von Hippel, Hazel Shackleton, Mike Dodds

llms agents benchmarks

arXiv AI

3d ago

Self-Spec Verifiable Code Generation

arXiv:2609.39568v1 Announce Type: cross Abstract: Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable...

By Jiaru Qian, Yihong Dong, Yongmin Li, Hao Zhu, Bin Gu, Ge Li

llms benchmarks

arXiv AI

4d ago

From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents

The paper introduces ReviveBench, a benchmark designed to evaluate coding agents’ ability to revive non‑running software and reconstruct industrial engines from open specifications. It comprises two families of tasks—revival (ten tasks addressing dependency issues, missing modules, legacy builds, and GPU models) and reconstruction (thirteen tasks covering numerical, geometric, hardware, and transactional systems). The benchmark uses hidden verifiers calibrated against native environments, engineering tools, or reference implementations, and the authors report that the strongest evaluated model passes all revival tasks and most reconstruction tasks, while also uncovering verifier defects that highlight measurement error in executable verification.

By Tianyu Liu, Dingyuan Dai, Yufan Du, Zhen Yang

agents benchmarks

arXiv AI

Sep 23

From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation

arXiv:2609.22664v1 Announce Type: cross Abstract: Research on large language model agents for penetration testing is evaluated almost entirely by capability: whether the agent captures a flag or repr...

By Joas Antonio dos Santos Barbosa

llms agents benchmarks safety

arXiv AI

Aug 21

Escaping the Quicksand: A Call to Arms

arXiv:2608. 19674v1 Announce Type: cross Abstract: Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk.

By Peter Sewell, Jean Pichon-Pharabod

One email a morning, machine-written

Related stories

Automated Hardware Validation Test Plan Generation for Large Scale AI Datacenter Platforms Using a Generative AI Multi-Agents Architecture

FVSpec: Real-World Property-Based Tests as Lean Challenges

Self-Spec Verifiable Code Generation

From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents

From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation

Escaping the Quicksand: A Call to Arms