SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suvarna, Ashima, Phan, Kendrick, Beikzadeh, Mehrab, Bansal, Hritik, Gabriel, Saadia
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.08477