EdgeAgentX让边缘设备在军用通信中更智能、更快、更抗干扰。

EdgeAgentX: A Novel Framework for Agentic AI at the Edge in Military Communication Networks

• 融合联邦学习与多智能体强化学习，实现分布式自主决策。
• 仿真显示延迟降低，吞吐量提升，抗攻击能力显著增强。
• 适合军事边缘计算场景，提升战场通信系统的韧性。

本文提出EdgeAgentX，一种融合联邦学习（FL）、多智能体强化学习（MARL）与对抗防御机制的新型框架，专为军事通信网络设计。通过综合仿真验证，该框架显著提升了自主决策能力，降低了延迟，增强了吞吐量，并能有效抵御对抗性干扰，展现出优异的鲁棒性。

原文摘要 · Abstract (English)

This paper introduces EdgeAgentX, a novel framework integrating federated learning (FL), multi-agent reinforcement learning (MARL), and adversarial defense mechanisms, tailored for military communication networks. EdgeAgentX significantly improves autonomous decision-making, reduces latency, enhances throughput, and robustly withstands adversarial disruptions, as evidenced by comprehensive simulations.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。