LLM代理的视觉指南
LLM Agents are becoming widespread, seemingly taking over the “regular” conversational LLM we are familiar with. These incredible capabilities are not easily created and require many components working in tandem.
LLM智能体正在变得越来越普遍，似乎正在取代我们熟悉的“常规”对话LLM。这些令人难以置信的能力并不容易创建，需要许多组件协同工作。
[
[
With over 60 custom visuals in this post, you will explore the field of LLM Agents, their main components, and explore Multi-Agent frameworks.
在这篇文章中，您将探索LLM智能体的领域、它们的主要组成部分，并探索多智能体框架，共有超过60个自定义视觉效果。
👈 click on the stack of lines on the left to see a Table of Contents (ToC)
👈 点击左侧的线条堆叠以查看目录 (ToC)
To understand what LLM Agents are, let us first explore the basic capabilities of an LLM. Traditionally, an LLM does nothing more than next-token prediction.
要理解LLM代理是什么，我们首先要探索LLM的基本能力。传统上，LLM仅仅是进行下一个标记的预测。
[
[
By sampling many tokens in a row, we can mimic conversations and use the LLM to give more extensive answers to our queries.
通过连续采样多个标记，我们可以模拟对话，并使用LLM为我们的查询提供更详细的答案。
[
[
](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F...