KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Thompson SamplingSimilar Papers 제목 키워드 기반
BayesOpt: A Bayesian Optimization Library for Nonlinear Optimization, Experimental Design and Bandits
BayesOpt is a library with state-of-the-art Bayesian optimization methods to solve nonlinear optimization, stochastic bandits or sequential experimental design problems. Bayesian optimization is sample efficient by build…
Bayesian OptimizationExperimental DesignHyperparameter OptimizationMetadata-based Multi-Task Bandits with Bayesian Hierarchical Models
How to explore efficiently is a central problem in multi-armed bandits. In this paper, we introduce the metadata-based multi-task bandit problem, where the agent needs to solve a large number of related multi-armed bandi…
Multi-Armed BanditsThompson SamplingBayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits
Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Despite the superior practical performance, their theoretical justification is less investigated in the lit…
Bayesian InferenceThompson SamplingInformation Directed Sampling for Stochastic Bandits with Graph Feedback
We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and cons…
Decision MakingThompson SamplingBayesian decision-making under misspecified priors with applications to meta-learning
Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The choice of prior in these algorithms offer…
Decision MakingMeta-LearningMulti-Armed BanditsSequential Decision Making+1