Unlike traditional RAG (Retrieval-Augmented Generation), RLM treats document context as an external variable in a Python REPL environment. The LLM doesn't see the full document - instead, it writes ...
A minimal, educational implementation of the RLM inference paradigm from Recursive Language Models (Zhang, Kraska, Khattab — MIT CSAIL, Jan 2026). Zero external dependencies. Just Python stdlib + any ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results