用奖励预测误差控制记忆更新，大幅降低大模型长期记忆的计算开销。
D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
- 基于多巴胺信号机制，按奖励预测误差高低分流处理输入数据。
- 减少80%以上令牌消耗，消除传统方法的O(N²)写入延迟瓶颈。
- 适合需要持续学习与高鲁棒性的长期智能体应用。
自主大模型智能体需要结构化长时记忆，但现有‘追加-演化’系统如A-MEM存在O(N²)写入延迟和高昂令牌成本。本文提出D-MEM（多巴胺门控代理记忆），一种受生物启发的架构，通过基于奖励预测误差（RPE）的快慢路由系统，将短期交互与认知重构分离。轻量级评论家路由器评估输入的意外性与效用，常规低RPE输入直接跳过或缓存于O(1)快速缓冲区；而高RPE输入（如事实矛盾或偏好变化）触发‘多巴胺’信号，激活O(N)记忆演化管道以重构智能体知识图谱。为评估真实场景表现，引入LoCoMo-Noise基准，在长时间会话中注入可控对话噪声。实验表明，D-MEM降低超过80%的令牌消耗，消除O(N²)瓶颈，并在多跳推理与对抗鲁棒性上优于基线。通过选择性地门控认知重构，D-MEM为终身代理记忆提供了可扩展、低成本的基础。
原文摘要 · Abstract (English)
Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired architecture that decouples short-term interaction from cognitive restructuring via a Fast/Slow routing system based on Reward Prediction Error (RPE). A lightweight Critic Router evaluates stimuli for Surprise and Utility. Routine, low-RPE inputs are bypassed or cached in an O(1) fast-access buffer. Conversely, high-RPE inputs, such as factual contradictions or preference shifts, trigger a "dopamine" signal, activating the O(N) memory evolution pipeline to reshape the agent's knowledge graph. To evaluate performance under realistic conditions, we introduce the LoCoMo-Noise benchmark, which injects controlled conversational noise into long-term sessions. Evaluations demonstrate that D-MEM reduces token consumption by over 80%, eliminates O(N^2) bottlenecks, and outperforms baselines in multi-hop reasoning and adversarial resilience. By selectively gating cognitive restructuring, D-MEM provides a scalable, cost-efficient foundation for lifelong agentic memory.
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。