Saved in:
Bibliographic Details
Main Authors: Akyol, Emre Furkan, Dedeler, Mehmet, Tüzün, Eray
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.26142
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915965772496896
author Akyol, Emre Furkan
Dedeler, Mehmet
Tüzün, Eray
author_facet Akyol, Emre Furkan
Dedeler, Mehmet
Tüzün, Eray
contents Bug tracking systems play a crucial role in software maintenance, yet developers frequently struggle with low-quality user-submitted reports that omit essential details such as Steps to Reproduce (S2R), Observed Behavior (OB), and Expected Behavior (EB). We propose ImproBR, an LLM-based pipeline that automatically detects and improves bug reports by addressing missing, incomplete, and ambiguous S2R, OB, and EB sections. ImproBR employs a hybrid detector combining fine-tuned DistilBERT, heuristic analysis, and an LLM analyzer, guided by GPT-4o mini with section-specific few-shot prompts and a Retrieval-Augmented Generation (RAG) pipeline grounded in Minecraft Wiki domain knowledge. Evaluated on Mojira, ImproBR improved structural completeness from 7.9% to 96.4%, more than doubled the proportion of executable S2R from 28.8% to 67.6%, and raised fully reproducible bug reports from 1 to 13 across 139 challenging real-world reports.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26142
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ImproBR: Bug Report Improver Using LLMs
Akyol, Emre Furkan
Dedeler, Mehmet
Tüzün, Eray
Software Engineering
Artificial Intelligence
Bug tracking systems play a crucial role in software maintenance, yet developers frequently struggle with low-quality user-submitted reports that omit essential details such as Steps to Reproduce (S2R), Observed Behavior (OB), and Expected Behavior (EB). We propose ImproBR, an LLM-based pipeline that automatically detects and improves bug reports by addressing missing, incomplete, and ambiguous S2R, OB, and EB sections. ImproBR employs a hybrid detector combining fine-tuned DistilBERT, heuristic analysis, and an LLM analyzer, guided by GPT-4o mini with section-specific few-shot prompts and a Retrieval-Augmented Generation (RAG) pipeline grounded in Minecraft Wiki domain knowledge. Evaluated on Mojira, ImproBR improved structural completeness from 7.9% to 96.4%, more than doubled the proportion of executable S2R from 28.8% to 67.6%, and raised fully reproducible bug reports from 1 to 13 across 139 challenging real-world reports.
title ImproBR: Bug Report Improver Using LLMs
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2604.26142