Papers2

#Long-context reasoning

The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context

Xiaoyuan Liu, Tian Liang et al.Feb 12arXiv

This paper gives language models a 'wand' to manage their own memory, instead of relying on humans to stuff the prompt for them.

#Stateful language models#Pensieve paradigm#Context pruning

Recursive Language Models

Beginner

Alex L. Zhang, Tim Kraska et al.Dec 31arXiv

Recursive Language Models (RLMs) let an AI read and work with prompts that are much longer than its normal memory by treating the prompt like a big external document it can open, search, and study with code.

#Recursive Language Models#RLM#Long-context reasoning