Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bin, Yi, Jiang, Tianyi, Ding, Yujuan, Zhu, Kainian, Ma, Fei, Song, Jingkuan, Yang, Yang, Shen, Heng Tao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.02249