$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Peihao, Cai, Ruisi, Wang, Zhen, Mei, Hongyuan, Liu, Qiang, Li, Pan, Wang, Zhangyang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.04948