SLM, LLM or Agentic AI? Toward Intelligent UAV-Enabled WPT Systems in Low-Altitude Economy Networks

2026-06-30

AI Summary

This study addresses the challenge of efficiently and adaptively optimizing wireless power transfer for unmanned aerial vehicles (UAVs) in resource-constrained and dynamically changing low-altitude economic networks. To this end, the work proposes two language model–based intelligent optimization approaches: a lightweight small language model (SLM) architecture integrating geometric-aware path decoding and ensemble reasoning, and a multi-agent Agentic AI framework composed of an Initializer, Actor, Critic, and Reflector. The SLM leverages a pre-trained BERT backbone, enhanced UAV embeddings, and contextual feature extraction to achieve low computational complexity, minimal latency, and high energy efficiency. The Agentic AI framework, through closed-loop collaborative reasoning and iterative refinement, substantially enhances the joint performance of trajectory planning and wireless power transfer. Simulations demonstrate the superiority and novelty of both methods in their respective operational scenarios.

Abstract

Unmanned Aerial Vehicles (UAVs) have become key enabling platforms for low-altitude economic networks, yet achieving efficient and adaptive optimization under resource-constrained and dynamic environments remains challenging. This paper investigates language models for UAV-enabled Wireless Power Transfer (WPT) systems. First, a lightweight Small Language Model (SLM)-based solution is developed using a pre-trained BERT backbone, enhanced UAV embeddings and contextual features, a geometry-aware path decoder, and ensemble inference to achieve low complexity, low latency, and high energy efficiency. Second, an Agentic AI-based framework is designed to exploit the reasoning and interactive capabilities of Large Language Models (LLMs). It integrates four collaborative agents-Initializer, Actor, Critic, and Reflector-to form a closed loop of generation, optimization, evaluation, and reflection for iterative UAV path and energy optimization. Finally, simulations compare the SLM-, LLM-, and Agentic AI-based approaches.

Problem

• UAV
• Wireless Power Transfer
• Low-altitude Economy
• Resource-constrained Optimization
• Dynamic Environment

Innovation

• Small Language Model (SLM)
• Agentic AI
• Wireless Power Transfer (WPT)
• UAV path optimization
• Large Language Model (LLM)