LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems

2026-07-05

AI Summary

This work addresses critical limitations in drone swarms—such as inadequate situational awareness, intermittent connectivity, and cybersecurity vulnerabilities—in applications like search-and-rescue and environmental monitoring. The authors propose LAUS, a large language model (LLM)-centric agent architecture that integrates perception, memory, reasoning-planning, and action modules to enable closed-loop cognition and adaptive coordination. For the first time, the study systematically analyzes emerging security threats, including priority manipulation, and identifies key challenges such as hallucination-resistant reasoning, constrained deployment, and perception-reasoning attack resilience. By synergistically combining onboard/edge computing, 5G/6G communications, multimodal intelligence, and tailored security mechanisms, LAUS supports reliable operation under resource-constrained, highly dynamic conditions, laying a theoretical foundation for future high-autonomy, high-assurance drone swarm systems.

Abstract

Uncrewed Aerial Vehicle (UAV) swarms have significant potential for applications such as Search and Rescue (SAR) and environmental monitoring, but their real-world deployment is limited by a lack of situational awareness, intermittent connectivity, and significant cybersecurity risks. Agentic Artificial Intelligence (AI) represents a shift from standalone Large Language Model (LLM) toward closed-loop cognitive architectures that integrate perception, memory, reasoning/planning, and action to enable adaptive, goal-directed swarm behavior. Within this framework, Agentic AI provides a unifying structure for autonomous and adaptive swarm operations while expanding the system attack surface compared to conventional AI systems. This paper proposes LLM-Centric Agentic AI for UAV Swarms (LAUS) and reviews key enabling technologies such as onboard and edge computing, 5G/6G connectivity, multimodal intelligence, and cybersecurity mechanisms, and analyzes threats such as Priority Manipulation Attacks (PMA) that can distort decision-making and degrade network performance. Finally, it identifies open research challenges, including hallucination-resistant reasoning, onboard LLM deployment under SWaP constraints, and standardized security benchmarks for perception-reasoning attacks in agentic UAV systems.

Problem

• UAV swarms
• situational awareness
• intermittent connectivity
• cybersecurity risks
• agentic AI

Innovation

• LLM-Centric Agentic AI
• UAV Swarms
• Closed-loop Cognitive Architecture
• Priority Manipulation Attacks
• Onboard LLM Deployment