BRQGen：迭代式评估 Bug 报告完整性并按需生成追问
BRQGen: Towards Adaptive Completeness Assessment and Follow-Up Question Generation for Bug Reports
这篇提出了一个挺聪明的思路：不再机械地问固定数量的问题，而是按报告缺口按需追问，作者还放了 429 条真实数据集和多个模型的对比成绩。
BRQGen 是一个迭代框架，先判断 Bug 报告是否有缺失或模糊信息，只在必要时生成针对性的追问，报告完整则直接归类为充分。作者从 Home Assistant 和 Brave Browser 整理了 429 条不完整 Bug 报告的数据集，每条都包含维护者的真实追问及其回答标注。实验显示，1 小时内发出的追问，作者回复时间中位数在 Home Assistant 为 0.52 小时、Brave 为 1.45 小时，而 4 小时后才发问则延长到 9.76 和 13.49 小时。效果上，DeepSeek V4.1 Flash 覆盖了 1073 个真实追问中的 51.8%，Gemini 3 Flash Preview 在完整性评估上拿到 49.3% 的 macro-F1；若只看高严重度缺口，Qwen 3.8 Flash 的 macro-F1 可达 73.6%。
BRQGen: Towards Adaptive Completeness Assessment and Follow-Up Question Generation for Bug Reports
Many bug reports lack the necessary information required to reproduce issues. In early studies, large language models have been employed to generate follow-up questions to enhance incomplete reports. However, they ask a fixed number of questions regardless of whether the report is incomplete. We propose BRQGen, an iterative framework that identifies missing or ambiguous information in bug reports and generates targeted follow-up questions, only if necessary. Reports with no identified gaps are classified as sufficient. When the author responds, BRQGen evaluates whether the answers provide the requested information and generates further questions for any exposed gaps. We curated a novel dataset of 429 incomplete bug reports from Home Assistant and Brave Browser, each containing at least one maintainer follow-up question. Each question is mapped to the author's answer and assigned a label indicating whether the requested information could have been provided directly through the issue template. Earlier maintainer requests were associated with author responses, whereas delayed requests were associated with no response. Among responding authors, requests within one hour received median replies after 0.52 hours in Home Assistant and 1.45 hours in Brave, versus 9.76 and 13.49 hours after four hours. BRQGen covered 35.4% (Qwen 3.8 Flash) to 51.8% (DeepSeek V4.1 Flash) of the 1,073 ground-truth follow-up questions. DeepSeek V4.1 Flash managed to ask 45.7% of all detailed questions and 63.9% of all generic questions. Gemini 3 Flash Preview reached the highest macro-F1 for completeness assessment of 49.3%, but with a post-hoc analysis by getting only the gaps with high severities, Qwen 3.8 Flash reaches 73.6% macro-F1 score. Completeness assessment improved when at least one identified gap had high severity, and nearly all ground-truth questions were captured within the first two iterations.