发表机构
Sun Yat-Sen University; Singapore Management University（中山大学; 新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对编码智能体忽视仓库贡献规范的问题，提出RepoNorm方法，独立获取显式和隐式规范并验证其适用性，通过实验证明能显著提升规范遵循率。
AI 中文摘要
编码智能体产生的变更可能通过功能测试，却未能满足仓库贡献要求。遵循仓库特定规范需要识别分散在仓库各处的指南，并解释其条件和例外情况。检索和文档方法提供了一般性上下文，但智能体仍需确定哪些规范适用。我们引入了RepoNorm，独立于编码任务获取显式和隐式的仓库规范。它利用仓库证据检查规范内容和适用性，在需要时查阅Git历史，并将规范包交付给现有编码智能体。我们的评估使用了三个编码模型和来自RepoNormBench的121个任务。与没有额外生成指南的基线（Raw）相比，总体规范遵循率（NCR）的相对改进为7.42-10.77%，贡献NCR的相对改进为31.64-45.44%，提示省略NCR的相对改进为11.34-17.69%。所有三个编码模型在使用RepoNorm时，这些NCR指标的值也高于使用CodeWiki文档时的值。功能成功率显示相对于Raw的观察增益为5.79-9.09个百分点；配对比较未达到显著性阈值。在RepoNorm的默认配置下，抽样精度为86%。
英文摘要
Changes produced by coding agents can pass functional tests while leaving repository contribution requirements unmet. Following repository-specific norms requires identifying guidance dispersed across repository sources and interpreting its conditions and exceptions. Retrieval and documentation approaches supply general context, but agents must still determine which norms apply. We introduce RepoNorm to acquire explicit and implicit repository norms independently of coding tasks. It checks norm content and applicability using repository evidence, consults Git history when needed, and delivers norm packages to existing coding agents. Our evaluation uses three coding models and 121 tasks from RepoNormBench. Against the baseline with no additional generated guidance (Raw), relative improvements are 7.42-10.77% for Overall Norm Compliance Rate (NCR), 31.64-45.44% for Contribution NCR, and 11.34-17.69% for Prompt-omitted NCR. All three coding models also obtain higher values on these NCR measures with RepoNorm than with CodeWiki documentation. Functional success rates show observed gains of 5.79-9.09 percentage points over Raw; the paired comparisons do not reach the significance threshold. Sampled precision is 86% with RepoNorm's default configuration.
Comments20 pages, 5 figures
