KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
This work addresses the problem of inefficient coordination in multi-agent systems, which is significant for researchers and developers working on large-scale language models and multi-agent systems.
The authors tackled the challenge of dynamic expert coordination in multi-agent systems, achieving an optimal cost-performance balance with their proposed framework, KABB. KABB maintains high performance while keeping computational demands relatively low.
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.