SEApr 13

Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals

arXiv:2604.1177019.5h-index: 2
Predicted impact top 38% in SE · last 90 daysOriginality Incremental advance
AI Analysis

For developers using automated program repair, SpecTune offers a more precise debugging approach by mimicking human reasoning about program states, but the gains are incremental over existing LLM-based methods.

SpecTune improves automated program repair by using intermediate behavioral signals from LLM-generated postconditions, achieving better fault localization and patch generation than baselines.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes