paper-with-me

홈 › Papers

VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus

2025-10-28 · Chuyue Sun, Yican Sun, Daneshvar Amrollahi, Ethan Zhang, Shuvendu Lahiri, Shan Lu, David Dill, Clark Barrett arxiv

We introduce VeriStruct, a novel framework that extends AI-assisted automated verification from single functions to more complex data structure modules in Verus. VeriStruct employs a planner module to orchestrate the systematic generation of abstractions, type invariants, specifications, and proof code. To address the challenge that LLMs often misunderstand Verus' annotation syntax and verification-specific semantics, VeriStruct embeds syntax guidance within prompts and includes a repair stage to automatically correct annotation errors. In an evaluation on eleven Rust data structure modules, VeriStruct succeeds on ten of the eleven, successfully verifying 128 out of 129 functions (99.2%) in total. These results represent an important step toward the goal of automatic AI-assisted formal verification.

📄 PDF Abstract BibTeX arXiv:2510.25015

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FormalSpecCpp: A Dataset of C++ Formal Specifications created using LLMs

2025-02-21 · Madhurima Chakraborty, Peter Pirkelbauer, Qing Yi

FormalSpecCpp is a dataset designed to fill the gap in standardized benchmarks for verifying formal specifications in C++ programs. To the best of our knowledge, this is the first comprehensive collection of C++ programs…

Large Language Models Assisting Ontology Evaluation

2025-07-19 · Anna Sofia Lippolis, Mohammad Javad Saeedizade, Robin Keskisärkkä, Aldo Gangemi 외 arxiv

Ontology evaluation through functional requirements, such as testing via competency question (CQ) verification, is a well-established yet costly, labour-intensive, and error-prone endeavour, even for ontology engineering…

A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation

2025-07-29 · Wenbo Liu, Forbes Hou, Jon Zhang, Hong Liu 외 arxiv

As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these…

Code Generation

Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback

2025-08-14 · Osama Mohammed Afzal, Preslav Nakov, Tom Hope, Iryna Gurevych arxiv

Novelty assessment is a central yet understudied aspect of peer review, particularly in high volume fields like NLP where reviewer capacity is increasingly strained. We present a structured approach for automated novelty…

ATLAS: AI-Assisted Threat-to-Assertion Learning for System-on-Chip Security Verification

2026-03-01 · Ishraq Tashdid, Kimia Tasnia, Alexander Garcia, Jonathan Valamehr 외 arxiv

This work presents ATLAS, an LLM-driven framework that bridges standardized threat modeling and property-based formal verification for System-on-Chip (SoC) security. Starting from vulnerability knowledge bases such as Co…