MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
Abstract
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.
Keywords
Cite
@article{arxiv.2601.06789,
title = {MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences},
author = {Qihao Wang and Ziming Cheng and Shuo Zhang and Fan Liu and Rui Xu and Heng Lian and Kunyi Wang and Xiaoming Yu and Jianghao Yin and Sen Hu and Yue Hu and Shaolei Zhang and Yanbing Liu and Ronghao Chen and Huacan Wang},
journal= {arXiv preprint arXiv:2601.06789},
year = {2026}
}