paper-with-me

Papers

A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning

2025-12-17 · Daragh King, Vasileios Koutavas, Laura Kovacs arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.15816

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Guiding Safe Exploration with Weakest Preconditions

2022-09-28 · Greg Anderson, Swarat Chaudhuri, Isil Dillig

In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training. We present a novel neurosymbolic approach called SP…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning (RL)+1

InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs

2026-07-06 · Guangyuan Wu, Weining Cao, Zehui Tan, Yuan Yao 외 arxiv

Loop invariant inference is a fundamental yet challenging problem in program verification. Recent LLM-aided guess-and-check techniques have shown strong performance on single-loop programs, but they often struggle with p…

Combining Mechanical and Agentic Specification Inference for Move

2026-05-11 · Wolfgang Grieskamp, Teng Zhang, Vineeth Kashyap arxiv

In this paper, we describe early work on a specification inference tool for the Move Prover that combines a weakest-precondition (WP) analysis over Move bytecode with an agentic coding CLI such as Claude Code. Specificat…

SEMBridge: Tagless-Final Program Semantics with Weakest-Precondition and Bounded-Checking Interpretations

2026-05-29 · Eric Liang arxiv

Formal methods provide rigorous accounts of program behavior, but practical software engineering often works through executable libraries, tests, and incremental design. This paper presents SEMBridge, a small tagless-fin…

The Hoare-fol Tool

2019-12-17 · Maxime Folschette

This document presents the tool named ''Application of Hoare Logic and Dijkstra's Weakest Proposition Calculus to Biological Regulatory Networks Using Path Programs with Branching First-Order Logic Operators'' or Hoare-f…

Translation