UMEM：面向通用化内存的统一内存提取与管理框架

摘要

自进化记忆作为基于大语言模型的智能体的可训练参数，其提取（从经验中提炼洞见）与管理（更新记忆库）必须紧密协同。现有方法主要优化记忆管理，却将记忆提取视为静态过程，导致泛化能力不足——智能体积累的是实例特异性噪声而非稳健记忆。为此，我们提出统一记忆提取与管理框架（UMEM），这是一种通过联合优化大语言模型实现记忆同步提取与管理的自进化智能体框架。为缓解对特定实例的过拟合，我们引入语义邻域建模技术，并通过GRPO算法以邻域级边际效用奖励进行优化。该方法通过评估语义相关查询簇中的记忆效用，确保记忆的泛化能力。在五个基准测试上的大量实验表明，UMEM显著优于现有强基线模型，在多轮交互任务中最高提升10.67%的性能。此外，UMEM在持续进化过程中保持单调增长曲线。代码与模型将公开发布。

English

Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updating the memory bank) must be tightly coordinated. Existing methods predominately optimize memory management while treating memory extraction as a static process, resulting in poor generalization, where agents accumulate instance-specific noise rather than robust memories. To address this, we propose Unified Memory Extraction and Management (UMEM), a self-evolving agent framework that jointly optimizes a Large Language Model to simultaneous extract and manage memories. To mitigate overfitting to specific instances, we introduce Semantic Neighborhood Modeling and optimize the model with a neighborhood-level marginal utility reward via GRPO. This approach ensures memory generalizability by evaluating memory utility across clusters of semantically related queries. Extensive experiments across five benchmarks demonstrate that UMEM significantly outperforms highly competitive baselines, achieving up to a 10.67% improvement in multi-turn interactive tasks. Futhermore, UMEM maintains a monotonic growth curve during continuous evolution. Codes and models will be publicly released.

UMEM：面向通用化内存的统一内存提取与管理框架

UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory

摘要

Support