An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zhuang, Yi, Qiuping, Xiao, Keyang, Ji, Zongcheng, Liang, Hongliang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913010358943744
author Li, Zhuang
Yi, Qiuping
Xiao, Keyang
Ji, Zongcheng
Liang, Hongliang
author_facet Li, Zhuang
Yi, Qiuping
Xiao, Keyang
Ji, Zongcheng
Liang, Hongliang
contents With the rise of multi-core processors and distributed systems, concurrent programming has become essential yet challenging, primarily due to the non-deterministic nature of thread execution. Manually addressing concurrency bugs is time-consuming and error-prone. Automated Program Repair techniques provide a promising solution. However, developing an end-to-end concurrency bug repair tool is particularly challenging. Most existing tools rely on the assumption that bug-related information is readily available or that concurrency bug contexts are ideally extracted, which is often impractical in real-world scenarios. This paper introduces ConFixAgent, an LLM-driven agent capable of fixing various types of concurrency bugs in an end-to-end manner, eliminating the need for any prior bug-related information. Specifically, we propose a novel context extraction approach designed for concurrency bug repair, utilizing Static Happens-Before Graphs to identify bug-relevant sections.We implemented ConFixAgent and evaluated it across multiple benchmark sets. Our extensive experiments demonstrate that ConFixAgent significantly outperforms state-of-the-art tools in addressing diverse types of concurrency bugs, with its context extraction method markedly enhancing the accuracy of LLM-generated repair solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05753
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor
Li, Zhuang
Yi, Qiuping
Xiao, Keyang
Ji, Zongcheng
Liang, Hongliang
Software Engineering
With the rise of multi-core processors and distributed systems, concurrent programming has become essential yet challenging, primarily due to the non-deterministic nature of thread execution. Manually addressing concurrency bugs is time-consuming and error-prone. Automated Program Repair techniques provide a promising solution. However, developing an end-to-end concurrency bug repair tool is particularly challenging. Most existing tools rely on the assumption that bug-related information is readily available or that concurrency bug contexts are ideally extracted, which is often impractical in real-world scenarios. This paper introduces ConFixAgent, an LLM-driven agent capable of fixing various types of concurrency bugs in an end-to-end manner, eliminating the need for any prior bug-related information. Specifically, we propose a novel context extraction approach designed for concurrency bug repair, utilizing Static Happens-Before Graphs to identify bug-relevant sections.We implemented ConFixAgent and evaluated it across multiple benchmark sets. Our extensive experiments demonstrate that ConFixAgent significantly outperforms state-of-the-art tools in addressing diverse types of concurrency bugs, with its context extraction method markedly enhancing the accuracy of LLM-generated repair solutions.
title An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor
topic Software Engineering
url https://arxiv.org/abs/2604.05753