从RAG到Agentic RAG再到Agent Memory的演变

I have been learning about memory in AI agents, and found myself overwhelmed by all the new terms. It started with short-term and long-term memory. Then it became even more confusing with procedural, episodic, and semantic memory. But wait. Semantic memory reminded me of a familiar concept: Retrieval-Augmented Generation (RAG).

我一直在学习AI代理中的记忆，发现自己被所有新术语淹没。最初是短期记忆和长期记忆。然后变得更加混乱，包括程序性、情节性和语义记忆。但等等，语义记忆让我想起了一个熟悉的概念：检索增强生成（RAG）。

Could memory in agents be the logical next step after vanilla RAG evolved to agentic RAG? At its core, memory in agents is about transferring information into and out of the large language model (LLM)‘s context window. Whether you call this information ’memories’ or ‘facts’ is secondary to this abstraction.

在香草RAG演变为代理RAG之后，代理中的记忆是否是逻辑上的下一步？在其核心，代理中的记忆是关于将信息转移进出大型语言模型（LLM）的上下文窗口。无论你称这些信息为“记忆”还是“事实”，对这个抽象来说都是次要的。

This blog is an introduction to memory in AI agents from a different angle than you might see in other blogs. We will not talk about short-term and long-term memory (yet), but gradually evolve the naive RAG concept to agentic RAG and to memory in AI agents. (Note that this is a simplified mental model. The entire topic of agent memory is more complex under the hood and involves things like memory management systems.)

这篇博客从不同的角度介绍了AI代理中的记忆，可能与其他博客中看到的不同。我们不会谈论短期和长期记忆（还没有），而是逐步将天真RAG的概念演变为代理RAG，再到AI代理中的记忆。（请注意，这是一个简化的心理模型。代理记忆的整个主题在底层更复杂，涉及诸如记忆管理系统之类的内容。）

The concept of Retrieval-Augmented Generation (RAG) was introduced in 2020 (Lewis et al.) and gained popularity around 2023. It was the first concept to give a stateless LLM access to past conversations and knowledge it hadn’t seen and stored in its model weights during training (parametric knowledge).

检索增强生成（RAG）的概念于2020年首次提出（Lewis et al.），并在2023年左右获得了普及。它是第一个使无状态LLM能够访问过去的对话和在训练期间未见过并存储在其模型权重中的知识（参数知识）的概念。

The core idea of the naive RAG workflow is straightforward, as shown in the image below:

简单的RAG工作流程的核心思想是直接的，如下图所示：

Offline indexing stage: Store additional information in an external knowledge source (e.g., vector database)
离线索引阶段：...