While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.

翻译：尽管自主软件工程智能体正在重塑编程范式，但目前它们存在一个“封闭世界”的局限：它们试图从零开始或仅利用局部上下文来修复错误，而忽略了在GitHub等平台上可用的海量历史人类经验。现实世界中问题跟踪数据的非结构化和碎片化特性，阻碍了对这种开放世界经验的访问。本文提出MemGovern框架，旨在治理原始GitHub数据并将其转化为可供智能体使用的可操作经验记忆。MemGovern采用经验治理机制将人类经验转化为智能体友好的经验卡片，并引入一种智能体经验搜索策略，实现基于逻辑的人类专业知识检索。通过生成13.5万张受治理的经验卡片，MemGovern实现了性能的显著提升，在SWE-bench Verified基准上的问题解决率提高了4.65%。作为一种插件式方法，MemGovern为构建智能体友好的记忆基础设施提供了解决方案。