发表机构
Université de Montréal; Mila – Quebec AI Institute（蒙特利尔大学; 米拉-魁北克人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MemCodex自进化分层记忆系统，通过开放式程序进化调整层内实现与跨层组合，配合MemArena统一运行时，相比最强基线成功率提升10.1%，上下文令牌减少3.4倍，推理加速2.1倍。
AI 中文摘要
代理记忆面临异构的访问需求：单跳问题可能只需要一条证据，而多跳问题则必须结合来自多个来源的证据。预定义的记忆工作流无法适应这些多变的需求。近期的自适应方法在记忆组件及其组合上进行搜索或学习，但设计空间本身仍是预定义的。我们提出MemCodex，一个自进化的分层记忆系统，将经验组织为可执行的记忆程序，用于摘要、关系知识、可复用技能和潜在记忆。开放式程序进化通过重写每层程序的构建、索引、检索和路由方式，来探索层程序的开放设计空间，从而同时调整层内实现和跨层组合。在查询时，读取过程从粗粒度到细粒度遍历层级，一旦找到足够证据便停止，必要时下探至原始历史记录。我们进一步开发了MemArena，一个统一运行时，将异构数据和记忆系统置于公共接口之后。MemCodex相对于最强的自适应记忆基线，平均任务成功率提高了10.1%，同时使用的上下文令牌减少了3.4倍，推理速度提高了2.1倍。
英文摘要
Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evidence from multiple sources. Predefined memory workflows cannot adapt to these varying needs. Recent adaptive methods search or learn over memory components and their compositions, but the design space itself remains predefined. We introduce MemCodex, a self-evolving hierarchical memory system that organizes experience into executable memory programs for summaries, relational knowledge, reusable skills, and latent memory. Open-ended program evolution searches the open design space of layer programs by rewriting how each layer is constructed, indexed, retrieved, and routed, thereby adapting both within-layer implementations and cross-layer composition. At query time, reads traverse the hierarchy from coarse to fine and stop once sufficient evidence is found, descending to the original history when needed. We further develop MemArena, a unified runtime that places heterogeneous data and memory systems behind a common interface. MemCodex improves average task success by 10.1% relative to the strongest adaptive-memory baseline, while using 3.4x fewer context tokens and achieving 2.1x faster inference.
CommentsWork in progress
