SLM, LLM or Agentic AI? Toward Intelligent UAV-Enabled WPT Systems in Low-Altitude Economy Networks
2026-06-30 • Information Theory
Information Theory
AI summaryⓘ
The authors explore how language models can help improve wireless power transfer using drones, which is a tricky problem due to limited resources and changing conditions. They first create a simple language model based on BERT that uses special features to plan drone paths efficiently with low delay and energy use. Then, they build a more complex system with multiple AI agents that work together to continuously improve drone routes and energy transfer by generating, testing, and refining plans. Finally, they run simulations to compare these methods. The work focuses on balancing performance with computational needs in drone power systems.
Unmanned Aerial Vehicles (UAVs)Wireless Power Transfer (WPT)Small Language Model (SLM)BERTLarge Language Models (LLMs)Agentic AIPath OptimizationEnergy EfficiencyEnsemble InferenceMulti-agent Systems
Authors
Feibo Jiang, Li Dong, Lei Mao, Kezhi Wang, Xianbin Wang, Abbas Jamalipour
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.