Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Jusheng, Huang, Zimeng, Fan, Yijia, Liu, Ningyuan, Li, Mingyan, Yang, Zhuojie, Yao, Jiawei, Wang, Jian, Wang, Keze
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.07350
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916936533671936
author Zhang, Jusheng
Huang, Zimeng
Fan, Yijia
Liu, Ningyuan
Li, Mingyan
Yang, Zhuojie
Yao, Jiawei
Wang, Jian
Wang, Keze
author_facet Zhang, Jusheng
Huang, Zimeng
Fan, Yijia
Liu, Ningyuan
Li, Mingyan
Yang, Zhuojie
Yao, Jiawei
Wang, Jian
Wang, Keze
contents As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.
format Preprint
id arxiv_https___arxiv_org_abs_2502_07350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
Zhang, Jusheng
Huang, Zimeng
Fan, Yijia
Liu, Ningyuan
Li, Mingyan
Yang, Zhuojie
Yao, Jiawei
Wang, Jian
Wang, Keze
Artificial Intelligence
As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.
title KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2502.07350