Scholarlink

<p>Post-release user feedback is a major control signal for maintenance and evolution in modern software development, yet it is noisy, fragmented, and difficult to translate into developer-usable issue specifications. Large Language Models (LLMs) can assist this transformation, but they often hallucinate or over-commit when evidence is weak, conflicting, or incomplete, limiting their robustness in automated software engineering workflows. We propose AGR (Agent-Governed Retrieval-Augmented Generation), a framework that regulates evidence acquisition and generation decisions via agentic control. AGR first applies an agentic triage step to filter low-signal or off-topic feedback, then retrieves evidence from a three-category hierarchy comprising official documentation, historical bug reports, and targeted web sources. It further performs confidence-weighted fusion across authoritative categories and uses an agentic decision module to verify relevance and sufficiency, trigger additional retrieval or online search when needed, reuse prior reports via memory, and abstain when evidence-supported grounding cannot be established. We evaluate AGR on two open-source software ecosystems, Firefox and VS Code. Results show that AGR achieves strong decision accuracy in triage and evidence verification, and produces more actionable and engineering-useful issue specifications than both raw feedback and a strong LLM baseline, while reducing unsupported details.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From noisy feedback to evidence-aware issue specifications: an agent-governed retrieval-augmented generation approach

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Zhiyao Wang,
  • Jialong Li,
  • Xiujing Guo,
  • Tatsuhiro Tsuchiya

摘要

Post-release user feedback is a major control signal for maintenance and evolution in modern software development, yet it is noisy, fragmented, and difficult to translate into developer-usable issue specifications. Large Language Models (LLMs) can assist this transformation, but they often hallucinate or over-commit when evidence is weak, conflicting, or incomplete, limiting their robustness in automated software engineering workflows. We propose AGR (Agent-Governed Retrieval-Augmented Generation), a framework that regulates evidence acquisition and generation decisions via agentic control. AGR first applies an agentic triage step to filter low-signal or off-topic feedback, then retrieves evidence from a three-category hierarchy comprising official documentation, historical bug reports, and targeted web sources. It further performs confidence-weighted fusion across authoritative categories and uses an agentic decision module to verify relevance and sufficiency, trigger additional retrieval or online search when needed, reuse prior reports via memory, and abstain when evidence-supported grounding cannot be established. We evaluate AGR on two open-source software ecosystems, Firefox and VS Code. Results show that AGR achieves strong decision accuracy in triage and evidence verification, and produces more actionable and engineering-useful issue specifications than both raw feedback and a strong LLM baseline, while reducing unsupported details.