ImproBR: Bug Report Improver Using LLMs
For software developers and maintainers, ImproBR addresses the practical problem of poor user-submitted bug reports, though its evaluation is limited to a single domain (Minecraft).
ImproBR uses LLMs to automatically detect and improve low-quality bug reports by filling missing Steps to Reproduce, Observed Behavior, and Expected Behavior sections. On 139 real-world Minecraft bug reports, it boosted structural completeness from 7.9% to 96.4% and increased fully reproducible reports from 1 to 13.
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.