LLM代理需补足语义记忆，才能应对复杂多变的真实环境。
Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents
- 分离程序记忆与语义记忆，构建模块化认知架构
- 在动态环境中，传统LLM易因规则突变而失效
- 适合研究智能体、认知建模及真实场景AI的开发者
大型语言模型（LLMs）在文本生成、代码补全和对话连贯性等程序性任务上展现出前所未有的能力，其架构模仿了人类的程序记忆——通过练习自动化重复性、模式驱动的任务。然而，随着LLMs在现实应用中的广泛部署，其在复杂、不可预测环境中的局限性日益凸显。本文认为，尽管LLMs具有变革性，但其根本受限于对程序记忆的依赖。要使智能体能够应对‘棘手’的学习环境——规则不断变化、反馈模糊、新颖性常态化——必须为LLMs补充语义记忆与联想学习系统。通过采用解耦认知功能的模块化架构，可弥合狭窄的程序专长与真实世界问题解决所需的适应性智能之间的差距。
原文摘要 · Abstract (English)
Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These capabilities stem from their architecture, which mirrors human procedural memory -- the brain's ability to automate repetitive, pattern-driven tasks through practice. However, as LLMs are increasingly deployed in real-world applications, it becomes impossible to ignore their limitations operating in complex, unpredictable environments. This paper argues that LLMs, while transformative, are fundamentally constrained by their reliance on procedural memory. To create agents capable of navigating ``wicked'' learning environments -- where rules shift, feedback is ambiguous, and novelty is the norm -- we must augment LLMs with semantic memory and associative learning systems. By adopting a modular architecture that decouples these cognitive functions, we can bridge the gap between narrow procedural expertise and the adaptive intelligence required for real-world problem-solving.
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。