Spotlights：发现软件仓库中的改进机会
Spotlights: Discovering Improvement Opportunities in Software Repositories
浏览论文内容
中文总结 AI 辅助
本文提出优化机会发现任务及Spotlights系统，通过逻辑映射和代理审查在软件仓库中定位改进区域，实验表明能恢复多数专家目标并显著提升性能。
中文摘要 AI 辅助
编码代理和进化代码搜索系统一旦指定了目标和评估标准，就可以改进实现。将这些方法应用于现有软件仓库会引出一个更早的问题：对于高级工程目标，哪些实现选择值得调查？我们引入了“优化机会发现”这一任务，即在仓库级别识别候选源代码区域、解释它们与目标的关系并提出可能的更改。该任务以仓库、工程目标和可选的运行时证据（如离线遥测观察或配置文件）作为输入，不要求用户指定缺陷、瓶颈或代码位置。我们提出了Spotlights系统，该系统通过逻辑仓库映射、连续的代理审查以及可选的研究链接将候选方案与相关技术联系起来。我们在模型服务、文档检索、区块链排序和文档处理方面评估了Spotlights。在三个案例中，它恢复了九个专家选择目标中的七个。在可靠性研究中，排名前十的候选方案中有70%达到了规定的正确性和严重性阈值。在五次重复检索运行中，73.6%的候选出现次数在所有五次运行中都有匹配的源代码区域。Spotlights还重新发现了一个被隐藏的检索优化的目标，并将其与相关的平铺技术联系起来。在一项实现研究中，一个发现的更改将端到端页面处理运行时间减少了10.6%，同时保持了测量的输出质量。这些结果确立了优化机会发现作为介于广泛工程目标与后续实现和验证之间的一个独特且可经验评估的步骤。
英文摘要
Coding agents and evolutionary code-search systems can improve implementations once a target and evaluation criterion have been specified. Applying these methods to an existing software repository raises an earlier question: which implementation choices are worth investigating for a high-level engineering objective? We introduce \emph{optimization-opportunity discovery}, the repository-level task of identifying candidate source regions, explaining how they relate to the objective, and proposing possible changes. The task takes as input a repository, an engineering objective, and optional runtime evidence such as offline telemetry observations or profiles. It does not require the user to specify a defect, bottleneck, or code location. We present \emph{Spotlights}, a system that performs this task through logical repository mapping, successive agent reviews, and optional research linking candidates to relevant techniques. We evaluate Spotlights across model serving, document retrieval, blockchain ordering, and document processing. Across three cases, it recovers seven of nine expert-selected targets. In the reliability study, 70\% of the top ten candidates meet the stated correctness and severity thresholds. Across five repeated retrieval runs, 73.6\% of candidate occurrences have a matching source region in all five runs. Spotlights also rediscovers the target of a withheld retrieval optimization and connects it to a relevant tiling technique. In an implementation study, a discovered change reduces end-to-end page-processing runtime by 10.6\% while preserving measured output quality. These results establish optimization-opportunity discovery as a distinct and empirically evaluable step between a broad engineering objective and subsequent implementation and validation.
