受神经科学启发，构建可长期积累、自动调用的类人记忆系统。
Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
- 基于认知心理学设计三层记忆架构，支持情绪化摘要与快速检索。
- 默认使用直觉式处理，必要时才启动深度思考，减少幻觉。
- 适合需要持续对话的智能体，如客服、心理助手等场景。
大语言模型缺乏持久且结构化的长期记忆，难以实现上下文敏感的检索。单纯扩展上下文窗口无法解决此问题：最新研究表明，仅上下文长度增加就可能导致推理能力下降高达85%，即便具备完美检索能力亦如此。本文提出一种受神经科学启发的记忆框架，融合互补学习系统理论、认知行为疗法中的信念层级、双过程认知及模糊痕迹理论，围绕三大原则构建：（1）记忆具有情感价值而非仅内容——通过预先计算的情绪-关联摘要（情感向量）在涌现的信念层级中实现决策前的快速定位；（2）检索默认采用系统1，系统2按需升级——以自动扩散激活和被动提示为默认机制，仅在必要时启动主动检索，并引入分级认知状态以结构性缓解幻觉；（3）编码是主动、实时且依赖反馈的——丘脑门控机制负责信息分发，执行控制模块通过好奇心驱动探索形成概要，而非被动接收。七项功能属性规定了实现必须满足的条件。随着时间推移，系统逐步趋近于系统1处理模式——临床专家水平的计算类比——使交互成本随经验增长而降低，而非上升。
原文摘要 · Abstract (English)
Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that context length alone degrades reasoning by up to 85% - even with perfect retrieval. We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory, organized around three principles: (1) Memory has valence, not just content - pre-computed emotional-associative summaries (valence vectors) organized in an emergent belief hierarchy inspired by Beck's cognitive model enable instant orientation before deliberation; (2) Retrieval defaults to System 1 with System 2 escalation - automatic spreading activation and passive priming as default, with deliberate retrieval only when needed, and graded epistemic states that address hallucination structurally; and (3) Encoding is active, present, and feedback-dependent - a thalamic gateway tags and routes information between stores, while the executive forms gists through curiosity-driven investigation, not passive exposure. Seven functional properties specify what any implementation must satisfy. Over time, the system converges toward System 1 processing - the computational analog of clinical expertise - producing interactions that become cheaper, not more expensive, with experience.
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。