IEEE

Federated Discrete Prompt Tuning for Language Models Using Synthetic Examples

Abstract: Effective prompt tuning is critical for using generative AI models, such as large language models (LLMs) and small language models (SLMs), for domain-specific tasks. However, optimizing ...
InfoQ

MIT's Recursive Language Models Improve Performance on Long-Context Tasks

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Cory Benfield discusses the evolution of ...
VentureBeat

MIT’s new ‘recursive’ framework lets LLMs process 10 million tokens without context rot

Recursive language models (RLMs) are an inference technique developed by researchers at MIT CSAIL that treat long prompts as an external environment to the model. Instead of forcing the entire prompt ...
GitHub

Recursive Language Model patterns for Claude Code — handle massive contexts (10M+ tokens) by treating them as external variables.

You don't call RLM tools directly. You ask Claude to analyze large files, and Claude uses RLM behind the scenes. With these in place, Claude will autonomously detect when to use RLM instead of reading ...
GitHub

feat: Enable programmatic sub-LLM calls for RLM (Recursive Language Model) pattern

Enable true Recursive Language Model (RLM) capabilities in OpenCode by adding a built-in tool that allows the LLM to write code that programmatically invokes sub-LLM calls in loops, rather than ...