让大模型同时学会提取和管理记忆，提升长期学习的泛化能力。
UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
- 联合优化记忆提取与管理，避免只学特定经验
- 在多轮任务中提升10.67%表现，持续进化无退化
- 适合需要长期记忆的智能体研究者使用
自演化记忆是基于大语言模型（LLMs）智能体的可训练参数，其中记忆提取（从经验中提炼洞察）与记忆管理（更新记忆库）需紧密协同。现有方法主要优化记忆管理，将记忆提取视为静态过程，导致泛化性差，智能体积累的是特定实例噪声而非稳健记忆。为此，我们提出统一记忆提取与管理框架（UMEM），使大语言模型在自演化过程中同步完成记忆提取与管理。为缓解对特定实例的过拟合，引入语义邻域建模，并通过GRPO优化模型，以邻域级边际效用奖励为目标。该方法通过评估语义相关查询簇中的记忆效用，确保记忆的泛化性。在五个基准上的大量实验表明，UMEM显著优于多个强基线，在多轮交互任务中最高提升达10.67%。此外，UMEM在持续演化过程中保持单调增长曲线。代码与模型将公开发布。
原文摘要 · Abstract (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.
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。