Scaling automated formal verification to real-world projects requires resolving cross-module dependencies and global contexts, which are challenges overlooked by existing function-centric methods. We introduce RagVerus, a framework that synergizes retrieval-augmented generation with context-aware prompting to automate proof synthesis for multi-module repositories, achieving a 27% relative improvement on our novel RepoVBench benchmark -- the first repository-level dataset for Verus with 383 proof completion tasks. RagVerus triples proof pass rates on existing benchmarks under constrained language model budgets, demonstrating a scalable and sample-efficient verification.
@article{arxiv.2502.05344,
title = {RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation},
author = {Sicheng Zhong and Jiading Zhu and Yifang Tian and Xujie Si},
journal= {arXiv preprint arXiv:2502.05344},
year = {2025}
}