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

2026-03-24

AI Summary

This work addresses the challenges of deploying large language models (LLMs) in low-altitude wireless networks, where high energy consumption, limited bandwidth, and the difficulty of simultaneously ensuring real-time responsiveness and reliability pose significant constraints. To overcome these issues, the authors propose a hierarchical agent collaboration architecture: an onboard lightweight small language model (SLM) handles real-time perception and decision-making, while a base-station-hosted LLM performs deep reasoning and policy optimization. The framework integrates short- and long-term memory mechanisms, tool orchestration, and on-demand communication. Experimental results demonstrate that this approach significantly reduces communication overhead and energy consumption while maintaining real-time response capabilities, thereby enhancing intelligent decision-making in low-altitude networks. This study presents the first effective realization of efficient SLM–LLM collaboration in such aerial scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Low-Altitude Wireless Networks
• Large Language Models
• Computational Constraints
• Communication Limitations
• Real-time Reliability

Innovation

• Aerial Agentic AI
• Small Language Model (SLM)
• Large Language Model (LLM)
• Low-Altitude Wireless Networks
• Hierarchical Coordination