Aerial Agentic AI: Synergizing LLM and SLM for Low-Altitude Wireless Networks

TL;DR

This paper introduces Aerial Agentic AI, a hierarchical framework combining fast-thinking Small Language Models on UAVs with slow-thinking Large Language Models at base stations to enhance low-altitude wireless networks.

Contribution

It presents a novel hierarchical AI architecture that addresses computational, communication, and real-time challenges in LAWNs by integrating SLMs and LLMs for decentralized and centralized decision-making.

Findings

SLM-based agents enable real-time UAV perception and decision-making.

LLM-based agents perform deep reasoning and global knowledge management.

Hierarchical coordination improves efficiency and reliability in LAWNs.

Abstract

Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and mobile terminals, are emerging as a critical extension of 6G. However, applying Large Language Models in LAWNs faces three major challenges: 1) Computational and energy constraints; 2) Communication and bandwidth limitations; 3) Real-time and reliability conflicts. To address these challenges, we propose Aerial Agentic AI, a hierarchical framework integrating UAV-side fast-thinking Small Language Model (SLMs) with BS-side slow-thinking Large Language Model (LLMs). First, we design SLM-based Agents capable of on-board perception, short-term memory enhancement, and real-time decision-making on the UAVs. Second, we implement a LLM-based Agent system that leverages long-term memory, global knowledge, and tool orchestration at the Base Station (BS) to perform deep reasoning, knowledge updates, and strategy optimization. Third, we establish an efficient hierarchical coordination mechanism, enabling UAVs to execute high-frequency tasks locally while synchronizing with the BS only when necessary. Experimental results validate the effectiveness of the proposed Aerial Agentic AI.