提出四层认知架构，区分知识与记忆的持久性机制。
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
- 构建知识、记忆、智慧、智能四层结构，每层有不同持久性规则。
- 实验证明知识层可永久保留，而记忆层按艾宾浩斯规律衰减。
- 适合需要长期知识积累的AI系统开发者参考。
当前最具影响力的两个认知架构框架CoALA和JEPA均缺乏显式的知识层及其独立的持久性语义。这一缺失导致类别错误：系统对事实陈述施加认知衰减，或将事实与经验采用相同的更新机制。我们调研现有记忆系统的持久性语义，发现从Karpathy的LLM知识库到BEAM基准近乎零矛盾解决得分的八处收敛点，均指向架构上的共性缺陷。为此，我们提出四层分解架构（知识、记忆、智慧、智能），各层具有根本不同的持久性语义：无限覆盖、艾宾浩斯衰减、证据触发修订、瞬时推理。配套的Python和Rust实现证明该架构分离在工程上可行。尽管借用认知科学术语作为类比（如知识/记忆区分呼应图尔文三重分类），但各层是基于持久性语义需求的工程构造，非神经架构决定。我们主张这些区分需在工程实现中体现持久性语义，而现有任何框架或系统均未提供此能力。
原文摘要 · Abstract (English)
The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics. This gap produces a category error: systems apply cognitive decay to factual claims, or treat facts and experiences with identical update mechanics. We survey persistence semantics across existing memory systems and identify eight convergence points, from Karpathy's LLM Knowledge Base [10] to the BEAM benchmark's near-zero contradiction-resolution scores [22], all pointing to related architectural gaps. We propose a four-layer decom position (Knowledge, Memory, Wisdom, Intelligence) where each layer has fundamentally different persistence semantics: indefinite supersession, Ebbinghaus decay, evidence-gated revision, and ephemeral inference respectively. Companion implementations in Python and Rust demonstrate the architectural separation is feasible. We borrow terminology from cognitive science as a useful analogy (the Knowledge/Memory distinction echoes Tulving's trichotomy), but our layers are engineering constructs justified by persistence-semantics requirements, not by neural architecture. We argue that these distinctions demand distinct persistence semantics in engineering implementations, and that no current framework or system provides this.
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。