Recursive Language Model

An inference scheme in which a long prompt is held as a program variable and the model processes it via code and recursive calls.

2 articlesLast mentioned

A Recursive Language Model (RLM) is an inference scheme in which a long prompt is held as a variable in a program execution environment rather than placed entirely in the model's context; the language model writes code to slice and read the parts it needs and calls itself recursively on sub-problems. It was proposed by MIT researchers in 2025.

It is studied as a way to handle inputs far longer than the context window, and because the model decomposes the input programmatically, even small models can process long inputs.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Claude Code's Code Mode Runs Tools From JavaScript and Trims Token CostsAI in Practice ·

    This lines up with research on Recursive Language Models, or RLMs, from MIT CSAIL.

    Read article
  • Temperature, Attention and Context Rot: Model Mechanics Behind Agent DesignAI in Practice ·

    Recursive Language Models (RLMs) offer another path.

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.