让记忆系统像程序一样自我进化，解决长期智能体记忆失效问题
MemPro: Agentic Memory Systems as Evolvable Programs
- 将记忆构建-检索全流程视为可演化的程序，支持端到端优化
- 在多个数据集上仅用几轮迭代就超越静态和提示优化基线
- 适合需要长期记忆的智能体开发，尤其关注可维护性与适应性
长时程自主智能体需要记忆系统来保留历史信息、追踪状态演变并复用知识，突破有限上下文窗口限制。现有代理记忆系统通常采用记忆构建-检索（MCR）流水线，但多仅调整记忆库，部署后固定其余流程。这种固定设计难以应对多样任务失败模式，且随记忆库规模与结构演化而逐渐失配。为此，我们提出MemPro，一个系统级演进框架，将整个MCR流水线视为可演化的程序，而非仅调整记忆库或提示文本。MemPro维护可运行的记忆系统实现版本树，由演化代理迭代选择有潜力的版本，诊断重复失败，通过故障模式引导的编辑-调试-优化生成改进子版本。在LongMemEval、LoCoMo、HotpotQA和NarrativeQA上的实验表明，MemPro在数轮迭代内持续优于强基线，性能不断上升，并实现良好性能-成本权衡。代码已开源。
原文摘要 · Abstract (English)
Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow a memory construction-retrieval (MCR) pipeline, but often adapt mainly the memory bank while keeping the surrounding pipeline fixed after deployment. This fixed-pipeline design struggles to handle heterogeneous task-specific failure modes and can become misaligned with memory banks that evolve in scale and structure over time. To address these limitations, we propose MemPro, a system-level evolution framework that treats the entire MCR pipeline as an evolvable program rather than adapting only the memory bank or prompt text. MemPro maintains a version tree of runnable memory-system implementations, where an Evolving Agent iteratively selects promising versions, diagnoses recurring failures, and creates improved child versions through failure-mode-guided edit-debug refinement. Experiments on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA show that MemPro consistently outperforms strong static and prompt-level evolving baselines within a few iterations, continues to improve with evolution, and achieves a favorable performance-cost trade-off. Code is available at https://github.com/wanghai673/MemPro.
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。