A full tour through RAG, document context, and AI agents - from 2023 to 2026 🌎🤖
TL;DR · AI 摘要
Jerry Liu 在新加坡举办了 90 分钟工作坊全面回顾了从 2023 年到 2026 年 RAG、文档上下文和 AI 代理的发展历程。
核心要点
- RAG 模型在过去三年中经历了 12 大痛点的改进。
- 重新排序和查询重写对于提高检索效果至关重要。
- 随着模型的改进，将逻辑卸载到代理循环中使检索层变得更简单。
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- RAG、文档上下文和 AI 代理的发展
- RAG 模型的发展
- 12 大痛点的改进
- 重新排序和查询重写
- 提高检索效果
- 逻辑卸载到代理循环
- 简化检索层
- 文档解析的挑战
- 极其困难
- 现代代理形式
- 工作流和深入研究
- 历史背景
- 理解当前关注点
金句 / Highlights
值得收藏与分享的关键句。
RAG 模型在过去三年中经历了 12 大痛点的改进。
重新排序和查询重写对于提高检索效果至关重要。
文档解析仍然是一个极其困难的问题，即使在 2026 年也是如此。
@hexapode gave a comprehensive 90-min workshop at @aiDotEngineer Singapore last week that comprehensively traces through how topics like retrieval, agent loops, agentic workflows, and document https://t.co/6NDxPRIWlp" / X
A full tour through RAG, document context, and AI agents - from 2023 to 2026 
gave a comprehensive 90-min workshop at
Singapore last week that comprehensively traces through how topics like retrieval, agent loops, agentic workflows, and document understanding have evolved in the last 3 years. We’re excited to share the 116-page slide deck online. If you’re seeing this for the first time, you’ll get a sense of how all AI patterns have evolved since the very beginning. Including the following topics: 
The 12 pain points of naive RAG The importance of reranking and query-rewriting How we’ve increased offloaded logic to the agentic loop as models improved (and coincidentally, the retrieval layer can get simpler) Retrieval being the bottleneck as agents improved Why document parsing is an extremely hard problem, even now in 2026 Exploring parsing outputs, from markdown to chunks to structured JSON metadata Modern agent form factors around workflows and deep research If you’ve followed us or the space since the beginning, some of this will feel a bit nostalgic and will provide context on why our core focus today is narrowly focused on SOTA document parsing for agents. If you’re seeing this for the first time, hopefully there’s some useful historical context in here! Slides: drive.google.com/file/d/1IQ7G0a