KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
Abstract
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 introduce 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 customized 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.
Cite
Text
Zhang et al. "KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Zhang et al. "KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/zhang2025icml-kabb/)BibTeX
@inproceedings{zhang2025icml-kabb,
title = {{KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems}},
author = {Zhang, Jusheng and Huang, Zimeng and Fan, Yijia and Liu, Ningyuan and Li, Mingyan and Yang, Zhuojie and Yao, Jiawei and Wang, Jian and Wang, Keze},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {74966-74996},
volume = {267},
url = {https://mlanthology.org/icml/2025/zhang2025icml-kabb/}
}