Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

  • 类型：arxiv
  • 标识：2607.11111
  • 链接：https://arxiv.org/abs/2607.11111
  • 主分类：agent
  • 形态：method
  • 被引：2
  • 被引来源：Semantic Scholar
  • S2被引：2
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understanding. Recent methods attempt to mitigate this limitation through pre-repair repository exploration; however, their fix-driven strategies explore repositories without identifying the agent's knowledge gaps, often yielding imprecise context that fails to bridge the underlying understanding deficit. In this paper, we propose ACQUIRE, a QA-driven framework for software issue resolution. Mirroring how experienced developer
  • OpenAlex ID：W7168282741
  • OpenAlex DOI：10.48550/arxiv.2607.11111
  • DOI：10.48550/arxiv.2607.11111
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.11111
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：修复前先知：面向软件问题解决的 QA 驱动仓库知识获取
  • TLDR中文：基于 LLM 的编程 Agent 显著推动了自动化软件问题解决，但由于对仓库理解不足，仍易出现事实性错误。近期方法尝试通过修复前仓库探索来缓解此问题；然而，其修复驱动策略在未识别 Agent 知识缺口的情况下探索仓库，往往产生不精确的上下文，无法弥补潜在的理解不足。本文提出 ACQUIRE，一种面向软件问题解决的 QA 驱动框架，模拟经验丰富的开发者
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-15-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]