发表机构
Model Engineering College; APJ Abdul Kalam Technological University（模范工程学院; APJ阿卜杜勒·卡拉姆技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出智能体联邦学习（AFL）框架，通过客户端侧智能体（CSA）和服务器端编排智能体（SSOA）实现自适应训练，在CIFAR-10上优于FedAvg和FedProx，提升准确率、鲁棒性和通信效率。
AI 中文摘要
联邦学习（FL）使得分布式客户端能够在无需共享原始数据的情况下进行协作模型训练，因此适用于医疗、金融和边缘智能等隐私敏感的应用场景。然而，传统的联邦学习方法依赖于静态的客户端参与和固定的聚合策略，这限制了其在非独立同分布（non-IID）数据分布、异构客户端行为以及噪声或不可靠更新下的有效性。为解决这些问题，本文提出了一种智能体联邦学习（AFL）框架，该框架在客户端和服务器层面集成了轻量级的基于规则的自主智能体。所提出的框架引入了一个客户端侧智能体（CSA），能够动态调整本地训练参数、控制参与度并评估更新的可靠性，同时服务器端编排智能体（SSOA）执行质量感知的客户端选择和自适应聚合。与传统联邦学习方法不同，AFL在训练过程中实现了上下文感知的决策，提高了动态分布式环境中的适应性和鲁棒性。在CIFAR-10数据集上进行的广泛实验，涵盖了独立同分布（IID）、非独立同分布（non-IID）和噪声客户端设置，结果表明AFL始终优于包括FedAvg和FedProx在内的标准基线。实验结果显示，AFL在分类准确率、收敛速度、对损坏更新的鲁棒性以及通信效率方面均有提升。消融研究进一步证实了CSA和SSOA的互补贡献，而统计分析验证了所观察到的增益的显著性。所提出的AFL框架表明，将自主智能体推理融入联邦学习为智能、自适应和鲁棒的分布式学习系统提供了一种有效且实用的解决方案。
英文摘要
Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it suitable for privacy-sensitive applications such as healthcare, finance, and edge intelligence. However, conventional FL approaches rely on static client participation and fixed aggregation strategies, which limits their effectiveness under non-IID data distributions, heterogeneous client behavior, and noisy or unreliable updates. To overcome these issuess, this paper proposes an Agentic Federated Learning (AFL) framework that integrates lightweight rule-based autonomous agents at both client and server levels. The proposed framework introduces a Client-Side Agent (CSA) that dynamically adapts local training parameters, controls participa- tion, and evaluates update reliability, while a Server-Side Orchestrator Agent (SSOA) performs quality-aware client selection and adaptive aggregation. Unlike traditional FL methods, AFL enables context-aware decision-making during the training process, improving adaptability and robustness in dynamic distributed environments. Extensive experiments conducted on the CIFAR-10 dataset under IID, non-IID, and noisy-client settings demonstrate that AFL consistently outperforms standard base- lines including FedAvg and FedProx. Experimental results show improvements in classification accuracy, convergence speed, robustness against corrupted updates, and communication efficiency. Ablation studies further confirm the complementary contributions of CSA and SSOA, while statistical analysis validates the significance of the observed gains. The proposed AFL framework demonstrates that incorporating autonomous agentic reasoning into federated learning provides an effective and practical solution for intelligent, adaptive, and robust distributed learning systems.
