EdgeAgentX: A Novel Framework for Agentic AI at the Edge in Military Communication Networks
This addresses the need for resilient and efficient AI at the edge in military communications, though it appears incremental as it combines existing techniques.
The paper tackled the problem of autonomous decision-making in military communication networks by introducing EdgeAgentX, a framework integrating federated learning, multi-agent reinforcement learning, and adversarial defense mechanisms, resulting in reduced latency, enhanced throughput, and robust performance against disruptions as shown in simulations.
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.