A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning
This addresses a critical bottleneck in automated program verification for software developers and verification tools, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of loop invariant generation for automated program verification by introducing NeuroInv, a neurosymbolic approach that combines neural reasoning with verification-guided symbolic repair, achieving a 99.5% success rate on a benchmark of 150 Java programs.
Loop invariant generation remains a critical bottleneck in automated program verification. Recent work has begun to explore the use of Large Language Models (LLMs) in this area, yet these approaches tend to lack a reliable and structured methodology, with little reference to existing program verification theory. This paper presents NeuroInv, a neurosymbolic approach to loop invariant generation. NeuroInv comprises two key modules: (1) a neural reasoning module that leverages LLMs and Hoare logic to derive and refine candidate invariants via backward-chaining weakest precondition reasoning, and (2) a verification-guided symbolic module that iteratively repairs invariants using counterexamples from OpenJML. We evaluate NeuroInv on a comprehensive benchmark of 150 Java programs, encompassing single and multiple (sequential) loops, multiple arrays, random branching, and noisy code segments. NeuroInv achieves a $99.5\%$ success rate, substantially outperforming the other evaluated approaches. Additionally, we introduce a hard benchmark of $10$ larger multi-loop programs (with an average of $7$ loops each); NeuroInv's performance in this setting demonstrates that it can scale to more complex verification scenarios.