ImproBR：利用LLM的bug报告改进器
ImproBR: Bug Report Improver Using LLMs
AI总结：
ImproBR通过结合DistilBERT、启发式分析和LLM分析，提升bug报告的结构完整性、可执行性及可复现性，显著提高质量。
摘要：
bug跟踪系统在软件维护中起关键作用，但开发者常面临低质量用户提交的bug报告，缺少关键细节如重现步骤（S2R）、观察行为（OB）和预期行为（EB）。我们提出了ImproBR，一种基于LLM的流程，自动检测并改进bug报告，通过解决缺失、不完整和模糊的S2R、OB和EB部分。ImproBR采用混合检测器，结合微调的DistilBERT、启发式分析和LLM分析器，指导GPT-4o mini使用特定部分的少样本提示和基于Minecraft Wiki领域知识的检索增强生成（RAG）流程。在Mojira上评估，ImproBR将结构完整性从7.9%提升至96.4%，可执行S2R比例从28.8%提升至67.6%，并在139个挑战性真实世界报告中将可复现bug报告从1个增加到13个。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
