让编程智能体学会借鉴人类历史经验，提升代码修复能力。
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
- 将GitHub问题数据转化为可被智能体使用的经验卡片
- 在SWE-bench Verified上修复率提升4.65%至135K张经验卡片
- 适合想增强代码生成与修复能力的研究者和开发者
当前自主软件工程智能体受限于‘封闭世界’，仅凭局部上下文修复错误，忽视了GitHub等平台积累的海量人类开发经验。真实问题追踪数据结构混乱、碎片化，难以利用。本文提出MemGovern框架，通过经验治理将原始数据转化为智能体可用的经验卡片，并设计基于逻辑的智能体经验检索策略，实现对人类专家知识的精准调用。该框架生成了135,000张经治理的经验卡片，在SWE-bench Verified测试集上使代码修复成功率提升4.65%。作为即插即用方案，MemGovern为智能体构建了友好的记忆基础设施。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。