DISC: Dynamic Decomposition Improves LLM Inference Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Light, Jonathan, Cheng, Wei, Riviere, Benjamin, Yue, Wu, Oyamada, Masafumi, Wang, Mengdi, Yue, Yisong, Paternain, Santiago, Chen, Haifeng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Software Engineering 68T07, 68W40 I.2.6; I.2.7; I.2.8; D.2.3; F.2.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.16706