Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Xiaofeng, Huang, Heyan, Liao, Lizi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.03541