Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals

TL;DR

SpecTune enhances automated program repair by integrating intermediate behavioral signals and specification validation, leading to more precise fault localization and improved repair success.

Contribution

This paper introduces SpecTune, a novel framework that incorporates localized postconditions and validation signals into APR, leveraging LLM-generated specifications for better repair accuracy.

Findings

SpecTune improves fault localization accuracy.

SpecTune outperforms baseline APR methods.

Using validation signals increases repair reliability.

Abstract

Automated Program Repair (APR) has recently benefited from large language models (LLMs). However, most LLM-based APR approaches still rely primarily on coarse end-to-end signals from test-suite outcomes to guide repair, providing limited insight into where a program's internal logic deviates from its intended behavior. In contrast, human debugging often relies on intermediate reasoning about program states through localized correctness conditions or assertions. Inspired by this observation, we propose SpecTune, a specification-guided debugging framework that incorporates intermediate behavioral reasoning into APR. SpecTune decomposes the repair task into suspicious regions connected by execution checkpoints and derives localized postconditions representing expected program behaviors at those points. By executing the buggy program and evaluating these postconditions, SpecTune produces micro-level debugging signals that indicate mismatches between observed and intended behaviors, enabling more precise fault localization and targeted patch generation. To address the potential unreliability of LLM-generated postconditions, we introduce two complementary signals: a specification validation signal alpha, which estimates the consistency of generated postconditions using partially passing test cases, and a discriminative signal beta, which detects violations of validated postconditions during execution. With these signals, SpecTune safely leverages automatically generated specifications for APR. Experimental results show that SpecTune improves fault localization and APR effectiveness than the baselines.