MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

qihao wang, Ziming Cheng, shuo zhang, Fan Liu, Rui Xu, Heng Lian, Kunyi Wang, Yu_xm, Jianghao Yin, Sen Hu, Yue Hu, Shaolei Zhang, Yanbing Liu, RongHao Chen, Huacan Wang

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences: 59 upvotes on Hugging Face Daily Papers, #1 of 24 papers on 2026-01-14. Day-by-day upvote history. It lost 23 votes when the Hub removed votes in bulk.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.