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

While standard models suffer from context rot as data grows, MIT’s new Recursive Language Model (RLM) framework treats ...
InfoQ

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

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance on long-context tasks. RLMs use a programming environment to recursively ...
NPR

The Academic Minute

January 23, 2026 • On Binghamton University Week: We all have to have difficult conversations at work. How do we handle them best? Danielle Dunne, associate professor in the School of Management, ...