ImproBR: Bug Report Improver Using LLMs

TL;DR

ImproBR is an LLM-based pipeline that automatically enhances bug reports by filling in missing or ambiguous details, significantly improving report quality and reproducibility in software maintenance.

Contribution

The paper introduces ImproBR, a novel hybrid LLM-based system that automatically improves bug report quality by addressing missing and ambiguous report sections.

Findings

Structural completeness increased from 7.9% to 96.4%.

Executable S2R reports more than doubled from 28.8% to 67.6%.

Fully reproducible bug reports increased from 1 to 13.

Abstract

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.