让大模型自主管理记忆,提升长程推理能力
Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
- 将长短时记忆统一为工具动作,由模型自主决策存取
- 在五个长周期任务上优于现有方法,上下文利用更高效
- 适合需要持续学习与复杂推理的智能体应用
大语言模型代理在长程推理中受限于有限的上下文窗口,有效记忆管理至关重要。现有方法通常将长时记忆(LTM)和短时记忆(STM)分开处理,依赖启发式规则或辅助控制器,限制了适应性与端到端优化。本文提出统一框架Agentic Memory(AgeMem),将LTM与STM管理直接融入代理策略中。AgeMem将记忆操作表现为基于工具的动作,使大模型代理能够自主决定何时存储、检索、更新、总结或丢弃信息。为训练此类统一行为,我们提出三阶段渐进式强化学习策略,并设计步进式GRPO以应对记忆操作带来的稀疏与非连续奖励。在五个长周期基准测试中,AgeMem始终优于强记忆增强基线,跨多个LLM主干网络实现任务性能提升、高质量长时记忆及更高效的上下文使用。
原文摘要 · Abstract (English)
Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization. In this paper, we propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy. AgeMem exposes memory operations as tool-based actions, enabling the LLM agent to autonomously decide what and when to store, retrieve, update, summarize, or discard information. To train such unified behaviors, we propose a three-stage progressive reinforcement learning strategy and design a step-wise GRPO to address sparse and discontinuous rewards induced by memory operations. Experiments on five long-horizon benchmarks demonstrate that AgeMem consistently outperforms strong memory-augmented baselines across multiple LLM backbones, achieving improved task performance, higher-quality long-term memory, and more efficient context usage.
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。