KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

TL;DR

KABB is a novel framework that improves multi-agent system coordination by integrating semantic understanding and dynamic expert adaptation, balancing performance and computational efficiency.

Contribution

It introduces a knowledge-aware Bayesian bandit framework with a 3D knowledge distance model, dual-adaptation mechanism, and Thompson Sampling for expert selection.

Findings

Achieves optimal cost-performance balance in multi-agent coordination.

Maintains high performance with low computational demands.

Demonstrates effectiveness through extensive evaluation.

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 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.