FedAgentBench

FedAgentBench is a benchmark designed to evaluate the ability of large language model (LLM) agents to autonomously coordinate federated learning processes in healthcare settings, addressing operational challenges such as client selection and data harmonization.

Papers using FedAgentBench (1)

FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM Agents2025