MemGovern：通过借鉴受治理的人类经验增强代码智能体

摘要

尽管自主软件工程（SWE）智能体正在重塑编程范式，但目前存在"封闭世界"的局限性：它们试图从零开始或仅依赖本地上下文修复错误，却忽略了GitHub等平台上可获取的海量历史人类经验。现实世界中问题追踪数据的非结构化与碎片化特性，阻碍了对这些开放世界经验的获取。本文提出MemGovern框架，通过治理原始GitHub数据将其转化为智能体可操作的经验记忆。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，并引入智能体经验搜索策略实现逻辑驱动的人类专业知识检索。通过生成13.5万张治理后的经验卡片，MemGovern在SWE-bench Verified基准上的问题解决率显著提升4.65%。作为即插即用方案，MemGovern为构建智能体友好型记忆基础设施提供了解决方案。

English

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.

MemGovern：通过借鉴受治理的人类经验增强代码智能体

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

摘要

Support