arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.13258cs.LGcs.AIcs.SE
收藏

你的代码代理可以与你一同成长,借助结构化记忆

Your Code Agent Can Grow Alongside You with Structured Memory

Tsinghua University(清华大学)

Yi-Xuan Deng, Xiaoqin Liu, Yi Zhang, Guo-Wei Yang, Shuojin Yang

AI总结:

本文提出MemCoder框架,通过结构化记忆和实时反馈实现人类与AI的持续共进化,提升代码代理在复杂软件工程任务中的性能。

摘要:

尽管

英文摘要:

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal evolution of projects, failing to leverage the "reasoning trajectories" implicit in past successful practices. This limitation results in rigid behavioral logic and a lack of autonomous adaptability, ultimately hindering their ability to tackle complex, repository-level problems. To bridge this static-dynamic mismatch, we propose MemCoder, a framework designed to enable continual human-AI co-evolution. MemCoder first structures historical human experience to distill latent intent-to-code mappings from past commits. It then employs a self-refinement mechanism driven by verification feedback to correct agent behavior in real-time. Crucially, an experience self-internalization mechanism is introduced to crystallize human-validated solutions into long-term knowledge, thereby supporting sustained evolution. Experimental results on SWE-bench Verified demonstrate that MemCoder not only achieves State-of-the-Art (SOTA) performance but also delivers a 9.4% improvement in resolved rate over the general foundation model DeepSeek-V3.2. These findings indicate that equipping agents with the capability to co-evolve with humans via project history and real-time feedback effectively unlocks the potential of general models in complex software engineering tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑