Skip to the document
Madhuopen lab
Outcome School · Other AI topics11 min read

by Amit Shekhar · 19 May 2026

Recursive Language Models (RLMs)

Recursive Language Models (RLMs), a new way of using language models to handle very large inputs that do not fit in the model's context window.

2,136 words#llm#ai#machine-learning4 recall cards

Recursive Language Models (RLMs)
Read on Outcome School ↗then come back to lock it in
Before you read, guess

What issue do RLMs address regarding extended input sequences?

Ten seconds, a guess, then read — a wrong guess still makes the answer stick.

What this article covers

  1. What is a Recursive Language Model (RLM)?
  2. Why do we need RLMs?
  3. How an RLM works
  4. How the model writes and runs code
  5. Why RLMs work better
  6. Recursion inside RLMs
  7. How RLMs differ from simple chunking
  8. Advantages of RLMs
  9. Limitations of RLMs
  10. When to use RLMs
  11. RLM vs RAG
  12. A real use case
  13. Summary

The article lives on outcomeschool.com. Read it there, then come back: the tutor in the margin has read it and will answer questions, and the questions below check what stayed.

Before you go

In one sentence, what was this chapter about?

From memory, without scrolling up. Writing it is what makes it yours; the grade is only to show you what you had.

How sure?