让大模型智能记忆：自适应框架提升代理记忆效率
Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
- 用可学习的门控机制实现动态记忆检索
- 通过任务特异性反思优化记忆存储，提升利用率
- 支持离线与在线优化，适合需要长期记忆的场景
基于大语言模型的智能体已在多个领域广泛应用，其中记忆能力尤为关键。现有记忆机制多依赖人工设计，成本高且性能不佳，且忽视了交互场景中的记忆周期效应，难以针对特定环境优化。为此，本文提出一种数据驱动、自适应的记忆框架，通过建模记忆周期来优化大模型智能体。具体包括：设计MoE门控函数以提升记忆检索效率；引入可学习聚合过程增强记忆利用；开发任务特异性反思机制以动态调整记忆存储。该框架使智能体能在特定环境中自主学习有效记忆策略，支持离线与在线优化。我们在多个维度进行综合实验验证方法有效性，相关代码已开源。
原文摘要 · Abstract (English)
LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to higher labor costs and suboptimal performance. In addition, these methods overlook the memory cycle effect in interactive scenarios, which is critical to optimizing LLM-based agents for specific environments. To address these challenges, in this paper, we propose to optimize LLM-based agents with an adaptive and data-driven memory framework by modeling memory cycles. Specifically, we design an MoE gate function to facilitate memory retrieval, propose a learnable aggregation process to improve memory utilization, and develop task-specific reflection to adapt memory storage. Our memory framework empowers LLM-based agents to learn how to memorize information effectively in specific environments, with both off-policy and on-policy optimization. In order to evaluate the effectiveness of our proposed methods, we conduct comprehensive experiments across multiple aspects. To benefit the research community in this area, we release our project at https://github.com/nuster1128/learn_to_memorize.
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。