Storing context as a Python variable instead of in the prompt Allowing the LM to recursively explore and partition the context Avoiding "context rot" (performance degradation with long context) ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results