Agentic Federated Learning: The Future of Distributed Training Orchestration
2026-04-06 • Multiagent Systems
Multiagent SystemsArtificial Intelligence
AI summaryⓘ
The authors address challenges in Federated Learning (FL) caused by differences between clients and changing system conditions. They propose Agentic-FL, where AI agents using language models autonomously manage tasks both on the server and client sides to improve fairness and efficiency. Server agents help reduce biased selection of clients, while client agents adjust privacy and model settings based on device capabilities. The work also highlights potential issues like reliability problems and security risks, suggesting directions for building more robust multi-agent systems in FL.
Federated LearningStochastic HeterogeneityLanguage Model AgentsSelection BiasPrivacy BudgetModel ComplexityDecentralized SystemsMulti-Agent SystemsAlgorithmic JusticeSystem Dynamics
Authors
Rafael O. Jarczewski, Gabriel U. Talasso, Leandro Villas, Allan M. de Souza
Abstract
Although Federated Learning (FL) promises privacy and distributed collaboration, its effectiveness in real-world scenarios is often hampered by the stochastic heterogeneity of clients and unpredictable system dynamics. Existing static optimization approaches fail to adapt to these fluctuations, resulting in resource underutilization and systemic bias. In this work, we propose a paradigm shift towards Agentic-FL, a framework where Language Model-based Agents (LMagents) assume autonomous orchestration roles. Unlike rigid protocols, we demonstrate how server-side agents can mitigate selection bias through contextual reasoning, while client-side agents act as local guardians, dynamically managing privacy budgets and adapting model complexity to hardware constraints. More than just resolving technical inefficiencies, this integration signals the evolution of FL towards decentralized ecosystems, where collaboration is negotiated autonomously, paving the way for future markets of incentive-based models and algorithmic justice. We discuss the reliability (hallucinations) and security challenges of this approach, outlining a roadmap for resilient multi-agent systems in federated environments.