KVerus: Scalable and Resilient Formal Verification Proof Generation for Rust Code

2026-05-05

AI Summary

Current large language models struggle with cross-module dependencies and code/toolchain evolution in Rust formal verification, leading to fragile and unsustainable proofs. This work proposes a novel adaptive verification paradigm that bridges the gap between the semantic understanding of large models and the structural constraints of formal verification by constructing a dynamic knowledge base integrating dependency-aware program analysis, semantic lemma indexing, and an error-driven self-refinement mechanism. Built upon Verus with a retrieval-augmented architecture, the approach achieves an 80.2% verification rate on single-file benchmarks—significantly outperforming AutoVerus (56.9%)—and attains a 51.0% success rate on repository-scale benchmarks involving cross-file dependencies, compared to a mere 4.5% for the baseline. It also contributes 23 upstream-accepted formal proofs for the Asterinas kernel’s memory management module.

Abstract

Formal verification provides the highest assurance of software correctness and security, but its application to large-scale, evolving systems remains a major challenge. While large language models (LLMs) have shown promise in automating proof generation, they often fail in real-world settings due to their inability to handle complex cross-module dependencies or changes in the codebase or the verification toolchain. We identify the fundamental problem as the Semantic-Structural Gap: LLMs operate on semantic code patterns, whereas formal verification is governed by rigid structural dependencies, a disconnect that leads to brittle, unsustainable proofs. To bridge this gap, we propose a new paradigm of self-adaptive verification and present KVerus, a retrieval-augmented system for Verus-based Rust verification that can adapt to an evolving software environment. KVerus constructs a dynamic knowledge base of code metadata, lemma semantics, and toolchain specifics. By combining dependency-aware program analysis, semantic lemma indexing, and error-driven self-refinement, it can navigate intricate cross-file dependencies to synthesize proofs and automatically repair proofs when faced with common evolutionary changes. Across three single-file benchmarks, KVerus verifies 80.2% of tasks, outperforming the state-of-the-art AutoVerus (56.9%) and degrades less than AutoVerus under breaking Verus updates. On three repository-level benchmarks with cross-file dependencies, KVerus achieves a 51.0% success rate, compared to 4.5% for a multi-round prompting baseline. Finally, on the Asterinas Rust OS kernel, KVerus produces upstream-accepted proofs that verify 23 previously unverified functions (21.0% of proof code) in the memory-management module. KVerus represents a significant step towards making formal verification a scalable and sustainable practice for modern, security-critical software.

Problem

• formal verification
• Rust
• proof generation
• cross-module dependencies
• evolving software

Innovation

• self-adaptive verification
• retrieval-augmented LLM
• semantic-structural gap
• cross-module dependency
• proof repair