LLM Meets the Sky: Heuristic Multi-Agent Reinforcement Learning for Secure Heterogeneous UAV Networks

TL;DR

This paper presents a hierarchical optimization framework combining semidefinite relaxation and a novel LLM-guided multi-agent reinforcement learning approach to enhance physical layer security and energy efficiency in heterogeneous UAV networks.

Contribution

It introduces a new LLM-guided heuristic MARL method for UAV trajectory optimization considering energy and security trade-offs in heterogeneous networks.

Findings

Outperforms existing methods in secrecy rate and energy efficiency.

Demonstrates robustness across different UAV swarm sizes.

Effectively incorporates expert heuristics via LLM guidance.

Abstract

This work tackles the physical layer security (PLS) problem of maximizing the secrecy rate in heterogeneous UAV networks (HetUAVNs) under propulsion energy constraints. Unlike prior studies that assume uniform UAV capabilities or overlook energy-security trade-offs, we consider a realistic scenario where UAVs with diverse payloads and computation resources collaborate to serve ground terminals in the presence of eavesdroppers. To manage the complex coupling between UAV motion and communication, we propose a hierarchical optimization framework. The inner layer uses a semidefinite relaxation (SDR)-based S2DC algorithm combining penalty functions and difference-of-convex (d.c.) programming to solve the secrecy precoding problem with fixed UAV positions. The outer layer introduces a Large Language Model (LLM)-guided heuristic multi-agent reinforcement learning approach (LLM-HeMARL) for trajectory optimization. LLM-HeMARL efficiently incorporates expert heuristics policy generated by the LLM, enabling UAVs to learn energy-aware, security-driven trajectories without the inference overhead of real-time LLM calls. The simulation results show that our method outperforms existing baselines in secrecy rate and energy efficiency, with consistent robustness across varying UAV swarm sizes and random seeds.