jhssong/reportfl: ReportFL

Read full text
Authors: Jaehoon Song, Jeongju Sohn
Cited by: 0

Abstract

Description ReportFL is an LLM-based fault localization approach that adapts the AutoFL framework. While AutoFL utilizes execution-based coverage information, ReportFL replaces the coverage module with a semantic reasoning component that utilizes current and historical bug reports. Refer to README for details. Attribution & Citation This project is an adaptation of the AutoFL artifact by the COINSE Lab. We have maintained the original data structure while modifying the core localization logic to prioritize bug report data. License Note: As the original repository does not specify a license, this adaptation is provided for research and reproduction purposes only.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
7 January 2026