提炼通用智能的共性认知模式，指导大模型智能体设计
Applying Cognitive Design Patterns to General LLM Agents
- 从旧架构中提取反复出现的认知设计模式
- 发现当前大模型智能体在推理与交互中的能力缺口
- 为通用智能研究提供可复用的设计框架
人工智能（及通用人工智能）的一个目标是识别并理解实现通用智能所需的关键机制与表征。尽管不同研究团队和传统独立探索了多种认知架构，但普遍存在相似的过程与表征模式，即“认知设计模式”。如今，基于大语言模型（LLMs）的系统提供了探索通用智能的新机制组合。本文梳理了前变压器时代各类架构中反复出现的认知设计模式，并分析这些模式在使用LLM的系统中的体现，尤其聚焦于推理与交互式（“智能体”）应用场景。通过考察和应用这些共性模式，可预测当前智能体大模型系统的缺陷，并指引未来利用生成基础模型实现通用智能的研究方向。
原文摘要 · Abstract (English)
One goal of AI (and AGI) is to identify and understand specific mechanisms and representations sufficient for general intelligence. Often, this work manifests in research focused on architectures and many cognitive architectures have been explored in AI/AGI. However, different research groups and even different research traditions have somewhat independently identified similar/common patterns of processes and representations or "cognitive design patterns" that are manifest in existing architectures. Today, AI systems exploiting large language models (LLMs) offer a relatively new combination of mechanisms and representations available for exploring the possibilities of general intelligence. This paper outlines a few recurring cognitive design patterns that have appeared in various pre-transformer AI architectures. We then explore how these patterns are evident in systems using LLMs, especially for reasoning and interactive ("agentic") use cases. Examining and applying these recurring patterns enables predictions of gaps or deficiencies in today's Agentic LLM Systems and identification of subjects of future research towards general intelligence using generative foundation models.
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。