MemEvolve：智能体记忆系统的元进化
MemEvolve: Meta-Evolution of Agent Memory Systems
December 21, 2025
作者: Guibin Zhang, Haotian Ren, Chong Zhan, Zhenhong Zhou, Junhao Wang, He Zhu, Wangchunshu Zhou, Shuicheng Yan
cs.AI
摘要
自进化记忆系统正以前所未有的方式重塑基于大语言模型的智能体进化范式。现有研究主要依赖人工设计的记忆架构来存储轨迹、提炼经验并合成可复用工具，使智能体能在环境交互中实时进化。然而，这种范式本质上受限于记忆系统自身的静态特性：虽然记忆能促进智能体层面的进化，但其底层架构无法针对多样化任务场景进行元适应。为突破这一局限，我们提出MemEvolve框架，通过联合进化智能体的经验知识与记忆架构，使智能体系统不仅能积累经验，还能持续优化其学习机制。为将MemEvolve植根于现有研究并促进未来自进化系统的开放发展，我们构建了EvolveLab统一代码库——该平台将十二种代表性记忆系统提炼为模块化设计空间（编码、存储、检索、管理），既提供标准化实现基础，也构建了公平的实验环境。在四大挑战性智能体基准测试上的广泛实验表明，MemEvolve实现了：（I）显著性能提升，将SmolAgent、Flash-Searcher等框架性能最高提升17.06%；（II）强大的跨任务与跨模型泛化能力，其设计的记忆架构能有效迁移至不同基准测试与骨干模型。
English
Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the staticity of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this gap, we propose MemEvolve, a meta-evolutionary framework that jointly evolves agents' experiential knowledge and their memory architecture, allowing agent systems not only to accumulate experience but also to progressively refine how they learn from it. To ground MemEvolve in prior research and foster openness in future self-evolving systems, we introduce EvolveLab, a unified self-evolving memory codebase that distills twelve representative memory systems into a modular design space (encode, store, retrieve, manage), providing both a standardized implementation substrate and a fair experimental arena. Extensive evaluations on four challenging agentic benchmarks demonstrate that MemEvolve achieves (I) substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to 17.06%; and (II) strong cross-task and cross-LLM generalization, designing memory architectures that transfer effectively across diverse benchmarks and backbone models.