← Library

1. Recursive Self-Aggregation: Deep Thinking and Test-Time Scaling for LLM Reasoning

   Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Vedant Shah, Johan Obando-Ceron, Yoshua Bengio, Brian Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin, Moksh Jain · Recursive Self-Aggregation Research

   RSA aggregates multiple chains-of-thought across iterations to unlock deep reasoning in LLMs. Aggregation-aware RL further boosts performance across math, coding, and knowledge tasks.

2. rsa-llm.github.io

   rsa-llm.github.io

   Source link only

3. GitHub - tobi/qmd: mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

   GitHub

   mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local - tobi/qmd