# Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach

arXiv: https://arxiv.org/abs/2607.18604 · HTML: https://mlsanity.com/paper/2607.18604/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control](https://mlsanity.com/paper/2103.02142/) (2021)
- [3D Aerial Highway: The Key Enabler of the Retail Industry Transformation](https://mlsanity.com/paper/2009.09477/) (2020)
- [Reinforcement Learning for Joint V2I Network Selection and Autonomous Driving Policies](https://mlsanity.com/paper/2208.02249/) (2022)
- [Multi-UAV Speed Control with Collision Avoidance and Handover-aware Cell Association: DRL with Action Branching](https://mlsanity.com/paper/2307.13158/) (2023)
- [Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks](https://mlsanity.com/paper/2405.11331/) (2024)
- [Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks](https://mlsanity.com/paper/2506.06532/) (2025)
- [Dynamics of Laser-Charged UAVs: A Battery Perspective](https://mlsanity.com/paper/2008.13316/) (2020)
- [HAPS-ITS: Enabling Future ITS Services in Trans-Continental Highways](https://mlsanity.com/paper/2105.04756/) (2021)
- [RL-Based Cargo-UAV Trajectory Planning and Cell Association for Minimum Handoffs, Disconnectivity, and Energy Consumption](https://mlsanity.com/paper/2312.02478/) (2023)
- [CVaR-Based Variational Quantum Optimization for User Association in Handoff-Aware Vehicular Networks](https://mlsanity.com/paper/2501.08418/) (2025)

## Abstract (arXiv)

The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.