LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies and Open Problems
LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems
AI summary
The paper proposes LAUS, an LLM-centric agentic AI framework for UAV swarms that integrates perception, memory, reasoning and planning, and action into a closed-loop cognitive architecture. It reviews enabling technologies such as onboard/edge computing, 5G/6G and multimodal intelligence, and analyzes threats such as priority manipulation attacks (PMA) that can distort decisions and degrade network performance. Open challenges include hallucination-resistant reasoning, onboard LLM deployment under SWaP constraints, and standardized security benchmarks for perception-reasoning attacks.