用大模型驱动无人机群，实现智能协同与自主决策。
LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems
- 以大模型为核心构建闭环认知架构，整合感知、记忆、推理与行动。
- 提出新型安全威胁如优先级操纵攻击，可能破坏集群决策效率。
- 适合研究智能无人系统、边缘计算与可信AI的学者参考。
无人飞行器（UAV）集群在搜救和环境监测等场景中潜力巨大，但实际部署受限于情境感知不足、连接间歇性及显著的网络安全风险。代理式人工智能（Agentic AI）正从单一大语言模型（LLM）演进为集成感知、记忆、推理/规划与行动的闭环认知架构，支持自适应、目标导向的集群行为。在此框架下，代理式AI为自主集群运作提供统一结构，但相比传统AI系统扩大了攻击面。本文提出面向无人机集群的基于大模型的代理式人工智能（LAUS），综述了机载与边缘计算、5G/6G通信、多模态智能及安全机制等关键技术，并分析了优先级操纵攻击（PMA）等威胁，该攻击可扭曲决策并降低网络性能。最后，识别出开放挑战：抗幻觉推理、在尺寸-重量-功耗（SWaP）约束下部署机载大模型，以及针对感知-推理攻击的标准化安全评估基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。