cs.ROFeb 23, 2026

Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial

Authors: Yousef Emami, Hao Zhou, Radha Reddy, Atefeh Hajijamali Arani, Biliang Wang, Kai Li, Luis Almeida, Zhu Han

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Uncrewed Aerial Vehicles (UAVs) are widely deployed across diverse applications due to their mobility and agility. Recent advances in Large Language Models (LLMs) offer a transformative opportunity to enhance UAV intelligence beyond conventional optimization-based and learning-based approaches. By integrating LLMs into UAV systems, advanced environmental understanding, swarm coordination, mobility optimization, and high-level task reasoning can be achieved, thereby allowing more adaptive and context-aware aerial operations. This survey systematically explores the intersection of LLMs and UAV technologies and proposes a unified framework that consolidates existing architectures, methodologies, and applications for UAVs. We first present a structured taxonomy of LLM adaptation techniques for UAVs, including pretraining, fine-tuning, Retrieval-Augmented Generation (RAG), and prompt engineering, along with key reasoning capabilities such as Chain-of-Thought (CoT) and In-Context Learning (ICL). We then examine LLM-assisted UAV communications and operations, covering navigation, mission planning, swarm control, safety, autonomy, and network management. After that, the survey further discusses Multimodal LLMs (MLLMs) for human-swarm interaction, perception-driven navigation, and collaborative control. Finally, we address ethical considerations, including bias, transparency, accountability, and Human-in-the-Loop (HITL) strategies, and outline future research directions. Overall, this work positions LLM-assisted UAVs as a foundation for intelligent and adaptive aerial systems.

Figures & tables

SurveysFocus & ScopeKey Findings / Application Categories
[ 22 ]A broad overview of integrating various LLMs (BERT, GPT, T5, etc.) with UAVs to enhance autonomous systems.Applications in natural language control, real-time data analysis, and mission planning for domains like surveillance and disaster response.
[ 24 ]Analyzes 17 papers to map the research landscape (2021–2024).Applications: UAV Optimization (35%), Adaptation (40%), Communication (25%). Models: GPT most used (58%). Highlights challenges, including hardware limitations, latency, security, and ethical alignment.
[ 25 ]Focuses on revolutionizing UAV-assisted wireless communication, information perception, and autonomous control.Enhances aerial networking, edge computing, multimodal data fusion, scene understanding, and path planning.
[ 26 ]Comprehensively surveys Transformer-based models (ViTs, STTs, etc.) and LLMs for UAV systems.Categorizes architectures for object detection, tracking, navigation, and mission planning. Highlights LLMs for high-level reasoning and interaction.
[ 27 ]Analyzes 74 papers and 56 projects across 9 core tasks in the UAV workflow.Academia: Broad, theoretical focus (e.g., multi-UAV planning). Industry: Practical focus on flight control, single-UAV planning, and human–machine interaction.
[ 28 ]A systematic review of LLM and MLLM integration in autonomous driving systems.Explores applications in perception, prediction, planning, decision-making, multitasking processing, and HMI. Discusses multimodal fusion, prompt engineering, and distillation, outlining challenges and future directions.
Table I : A summary of existing surveys on the integration of LLMs and MLLMs in UAV Operation and Communication.
Figure 1: Overall organization of the survey, illustrating the research foundations, LLM adaptation stack, core application domains (LLM-enabled communications and MLLM-driven intelligence), and responsible and future intelligence considerations for UAV systems.
Figure 2: LLM fine-tuning pipeline for UAV applications, showing the progression from a pretrained language model through UAV-specific data preparation, model and training setup, parameter-efficient fine-tuning (e.g., adapters, LoRA/QLoRA, and prompt tuning), followed by evaluation, deployment, continuous monitoring, and updates to produce a UAV-adapted LLM.
ReferenceProposed FrameworkPrimary Application DomainCore Technical ApproachKey Performance Results
[ 34 ]Hybrid LLM–RAG Decision-Making SystemIoD, Autonomous UAV MissionsLLM integrated with RAG over a knowledge graph built from real-time sensor data and historical mission logs; fully auditable decision tracing92% decision accuracy; 94% mission success rate in dynamic environments
[ 35 ]Augmented LLM–RAG IoD Decision ModelIoD, Multi-UAV Network CoordinationCentralized LLM with RAG processing telemetry, mission logs, and environmental data for real-time contextual decisionsBLEU score: 0.82; cosine similarity: 0.87; average decision latency: 120 ms
[ 36 ]LLM-LandAutonomous UAV LandingLightweight LLM with RAG combined with a Vision-Language Encoder (VLE) and Model Predictive Control (MPC) for semantic constraint-aware trajectory replanningHigh landing success rate; superior obstacle avoidance compared to baseline MPC and non-RAG LLM-MPC; real-time feasibility on constrained hardware
[ 37 ]LLM–RAG UAV-BS Optimization FrameworkUAV-assisted Mobile Networks (UAV-BSs)GAI-assisted LLM with RAG (e.g., GPT-4) to automate mathematical modeling and optimize UAV placement strategiesFaster convergence and higher efficiency than Genetic Algorithm-based approaches
[ 38 ]GraphRAGGeneral RAG Enhancement (incl. UAV Analytics)Knowledge-graph-based retrieval of nodes, subgraphs, and communities instead of isolated text chunksImproved query-focused summarization; reduced redundancy; enhanced global domain understanding
[ 39 ]HybridRAGDomain-Specific Analytics (e.g., UAV Systems)Combination of VectorRAG for semantic similarity and GraphRAG for structured relational reasoningMore faithful, comprehensive, and domain-aligned LLM responses
Table II : Summary of RAG frameworks applied to UAV operation and communication systems, covering decision-making, network optimization, autonomous landing, edge computing, and evaluation methodologies.
Figure 3: Conventional RAG pipeline for UAV applications, illustrating the workflow from UAV task/query formulation through task-aware query encoding, hybrid knowledge retrieval (vector, graph, and hybrid RAG), context augmentation, and grounded LLM-assisted response generation using domain-specific UAV knowledge sources.
Figure 4: Prompt engineering strategies for UAV applications, comparing in-context learning, chain-of-thought prompting, prompt-based planning, and self-refinement in terms of prompt structure, LLM roles, and resulting capabilities for reliable, scalable, and robust UAV decision-making.
ReferenceProposed FrameworkPrimary Application DomainCore Function of the LLMKey Advantage over Traditional MethodsKey Performance Results
[ 44 ]ICLDCUASNets, SAR EmergenciesEdge-deployed LLM uses ICL to generate data collection schedules from natural-language task descriptions derived from sensory logsEliminates iterative DRL training; enables rapid adaptation, improved safety via verifier, and robustness through attack detectionSignificant reduction in cumulative packet loss vs. DQN and Maximum Channel Gain; faster convergence and lower computational overhead
[ 45 ]FRSICLUAV-Assisted Wildfire MonitoringLLM performs real-time flight resource allocation by jointly optimizing data collection schedules and UAV velocities using contextual task descriptionsJoint optimization without retraining; improved responsiveness and stability compared to policy-gradient and heuristic methodsLower average AoI and more stable velocity control than PPO and Nearest-Neighbor baselines
[ 46 ]LLM-Assisted ICL for Public Safety UAVsDisaster Response and Wildfire MonitoringEdge LLM leverages prompts and demonstrations to adaptively control UAV path planning, velocity, scheduling, and power managementGeneralizes across tasks without retraining; flexible prompt-based control versus task-specific optimization modelsSignificant packet loss reduction in data collection; highlights resilience and exposure to jailbreaking vulnerabilities
[ 47 ]AIC-VDSMulti-UAV Post-Disaster Monitoring (e.g., Tsunami Response)Attention-guided LLM focuses on urgent sensors to generate task descriptions for joint scheduling and velocity controlEfficient compression of high-dimensional sensory data; scalable coordination beyond multi-agent DRL limitsUp to 91% packet loss reduction compared to Multi-agent DQN and Maximum Channel Gain baselines
[ 48 ]LLM-CRFHuman–Swarm Teaming for Disaster SARCentral LLM interprets multi-modal human commands, extracts intent, and performs hierarchical task decomposition and mission planningTransforms human role from low-level control to high-level supervision; improves safety with ICL and HITL verification64.2% reduction in task completion time; 94% mission success rate; 42.9% reduction in operator cognitive workload
Table III : ICL frameworks leveraging LLMs for emergency UAV and sensor network operations, comparing approaches for data collection, wildfire monitoring, disaster response, multi-UAV coordination, and human–swarm teaming in search and rescue.
AspectLLM Pre-trainingLLM Fine-tuningPrompt EngineeringRAG
Core ObjectiveLearn general language patterns, knowledge, and reasoning abilities from a massive corpus.Adapt a pretrained model’s knowledge to a specific task or domain using a smaller dataset.Guide the output of a pretrained model for a specific task by carefully designing the input prompt.Enhance the output of a pretrained model by retrieving and incorporating relevant, up-to-date information from an external knowledge base.
Primary InputMassive, general/specialized text corpora (e.g., web data, books, code).Smaller, task-specific, often labeled datasets.A carefully crafted textual prompt (instructions, examples, context).User query + relevant information retrieved from an external knowledge base.
Core ProcessUnsupervised next-token prediction on a vast dataset. Training from scratch.Updating model parameters (fully or via PEFT) on a targeted dataset.Designing and iteratively refining the input text. No weight updates.Retrieving relevant documents and augmenting the prompt with this context before generation.
Resource IntensityExtremely High. Vast data, immense compute (GPU clusters, 3D parallelism).Moderate to High. Lower than pre-training but still significant for full fine-tuning.Very Low. Requires only a forward pass; no training.Low to Moderate. Adds a retrieval step and a longer context, but inference-only.
Key AdvantagesDevelops foundational language capabilities and emergent skills.High task-specific performance, efficient transfer learning.Highly flexible, fast to implement, resource-efficient.Provides up-to-date & factual information, reduces hallucinations.
Key ChallengesProhibitively expensive/time-consuming. Requires vast domain-specific data.Computationally heavy for edge systems. Requires quality labeled data.Effectiveness depends heavily on the design of prompts.Requires building/maintaining a high-quality, updated knowledge base.
Table IV : Comparison of LLM adaptation techniques—pre-training, fine-tuning, prompt engineering, and RAG—in terms of their core objectives, inputs, processes, resource requirements, advantages, challenges, suitability for UAV applications, and basis of output generation.
Figure 5: Diagram of the LLM-assisted UAV navigation, planning, and placement framework, illustrating the integration of mission context, reasoning, decision-making, and multi-agent coordination for autonomous operations.
Ref.Proposed FrameworkAutonomy LayerPrimary Application DomainCore Function of the LLMKey Results / Advantages
[ 66 ]SPINE-based Air–Ground SystemMission-Level PlanningAir–Ground Cooperative Robotics in Unknown EnvironmentsInterprets natural language missions, infers semantic objects, and generates adaptive plans using online semantic–metric mappingSuccessfully completes language-specified missions in kilometer-scale urban and rural environments under intermittent connectivity
[ 67 ]MSDTMD-SG-Based Swarm PlanningPlanning / Path OptimizationUAV Swarm Path Planning for Industry 5.0 Rescue ScenariosLearns human-like multi-step reasoning for movement decisions via fine-tuned datasets and symbolic modelingHighest task completion rate compared to DRL and ACO baselines with competitive latency and improved interpretability
[ 68 ]LLM-assisted Multi-UAV PlacementNetwork-Level PlanningMulti-UAV IAB Network DeploymentIteratively generates and refines UAV placement using structured prompting and historical feedbackNear-optimal connectivity and coverage with significantly fewer iterations than conventional optimization methods
[ 69 ]NELVEnd-to-End Planning PipelineNatural Language–Driven UAV Mission ExecutionMaps language instructions to executable flight trajectories via parsing, route planning, control, and monitoringReduces pilot workload and enables multi-UAV missions while satisfying regulatory and environmental constraints
[ 70 ]FlockGPTExecution / Formation ControlNatural Language–Driven UAV Swarm FormationTranslates high-level geometric commands into executable formation control code using SDFsEnables intuitive swarm control for non-experts; effective formation execution without manual programming
[ 71 ]RALLYExecution / Hybrid ControlCollaborative UAV Swarm NavigationCombines LLM reasoning with MARL via role assignment and goal refinementImproves task success rate, convergence speed, and robustness over MARL-only baselines
Table V : Comparative overview of recent LLM-assisted UAV planning, coordination, and swarm control frameworks, highlighting their autonomy layers, application domains, core LLM functions, and demonstrated performance benefits across diverse mission scenarios.
ReferenceProposed FrameworkPrimary Application DomainCore Function of the LLMKey Advantage over Traditional MethodsKey Performance Results
[ 74 ]LLM–HFACS UAV Accident Investigation SystemUAV Safety Analysis and Accident InvestigationLLM reasons over unstructured incident narratives and maps findings to the structured HFACS 8.0 taxonomy to identify causal factors across multiple levelsAutomates and standardizes human-factor analysis; detects subtle latent errors with reduced time, cost, and human effort compared to manual expert codingMacro-F1 scores of 0.58–0.76 across 18 categories; best F1 of 0.76 (precision 0.71, recall 0.82); some category accuracies >> 93%
[ 75 ]LLM-assisted Satellite–UAV–IoT Network Optimization6G Integrated Satellite–UAV–IoT CommunicationsFine-tuned Llama 3 70B dynamically optimizes device association, resource allocation, and UAV positioning using real-time network telemetryReduces action-space complexity and decision latency; enables adaptive, predictive network management beyond static optimization and RL methods27% average spectral efficiency gain; 35% reduction in decision latency compared to traditional approaches
[ 76 ]LEDMA (LLM-Assisted Decomposition-Based MOEA)UAV Networks with ISACLLM acts as a black-box search operator to decompose and solve multi-objective optimization problems for UAV deployment and power controlImproves convergence and solution diversity for non-convex, high-dimensional optimization beyond classical evolutionary algorithmsBetter Pareto front, faster convergence, and higher hypervolume than traditional multi-objective evolutionary algorithms
[ 77 ]Embodied Aerial Intelligent AgentOpen-World Autonomous UAV OperationsEdge-deployed LLM performs high-level task planning and scene understanding, interfaced with low-level perception, mapping, and motion controlEnables robust autonomy and generalization in communication-constrained environments through hardware–software co-design14B-parameter LLM achieves 5–6 tokens/s at 220W; validated across diverse real-world missions (inspection, exploration, monitoring)
[ 78 ]LLM-Assisted Unmanned Traffic Management (UTM) SystemUAV Traffic Management and Airspace SafetyLLM analyzes real-time airspace data, checks compliance, and generates actionable alerts and recommendations for human operatorsEnhances situational awareness and decision support beyond rule-based monitoring systemsUp to 91.7% decision accuracy with an average response time of 5.7 seconds across evaluated scenarios
Table VI : LLM-enhanced frameworks for UAV safety, network optimization, and autonomous intelligence, comparing methodologies, core LLM roles, and performance improvements in accident investigation, integrated communications, multi-objective optimization, open-world autonomy, and traffic management.
Figure 6: Architectures for multi-LLM deployment in UAV swarms: parallel/ensemble for robust decision-making, hierarchical for tiered resource-aware intelligence, and distributed specialized agents for decentralized mission execution.
ReferenceProposed FrameworkPrimary Application DomainCore Function of the LLMKey Advantage over Traditional MethodsKey Performance Results
[ 80 ]Multi-LLM Distributed Coordination ParadigmHeterogeneous Aerial and UAV NetworksMultiple specialized LLMs collaboratively handle routing, communication optimization, collision avoidance, and mission-level coordination while sharing critical state informationEnables division of labor, real-time adaptation, fault tolerance, and collective optimization beyond single-LLM or centralized controllersImproved safety, efficiency, resilience, and scalability in heterogeneous aerial networks (conceptual and system-level validation)
[ 81 ]Multi-LLM UAV Swarm Inspection SystemUAV Swarm Infrastructure InspectionLightweight onboard LLMs perform local path planning and real-time decisions, while a centralized LLM orchestrator handles global reasoning and task allocationBalances local responsiveness with global optimization; improves robustness, coverage, and energy efficiency compared to traditional plannersHigher inspection coverage, improved energy efficiency, and more robust swarm coordination in dynamic inspection scenarios
[ 82 ]LLM-assisted Multi-Agent Inspection FrameworkAEC Industry UAV Visual InspectionSpecialized LLM agents (Router, PathPlanner, Controller, Perceptioner, Retriever) perform 3D reasoning, task delegation, perception, and UAV controlEnables spatial-semantic understanding via semantic point clouds and 3D scene graphs; improves automation over rule-based inspection systemsDemonstrates flexible task coordination and improved automation of complex inspection workflows
[ 55 ]Aero-LLMSecure and Resilient UAV OperationsHierarchical LLMs across onboard, edge, and cloud layers perform anomaly detection, forecasting, and cybersecurity analysisAchieves low-latency response and high-level reasoning while maintaining lightweight onboard computationStrong performance in threat detection and secure decision-making on resource-constrained UAV platforms
[ 84 ]Hierarchical LLM-Controlled Hybrid Aerial NetworkUAV–HAPS Terrestrial–Non-Terrestrial NetworksMeta-controller LLM on HAPS manages global resource allocation and load balancing, while onboard LLMs handle real-time motion and communication controlJoint optimization of motion and communication outperforms DRL and hybrid control schemes in complex aerial networksHigher system rewards, lower operational cost, and reduced collision rates compared to DRL and hybrid baselines
Table VII : Hierarchical and multi-LLM architectures for coordinated UAV and aerial network operations, comparing distributed, swarm-based, and layered LLM frameworks in inspection, security, and hybrid terrestrial–non-terrestrial network applications.
Figure 7: End-to-end multimodal reasoning and control frameworks for VLN in UAVs, featuring instruction grounding, hierarchical collaboration, and safety-aware execution for continuous 3D navigation.
ReferencePurposeInput ModalitiesModelsKey Outcomes / Achievements
[ 92 ]Human-swarm interaction, context-aware commandText, voice, teleoperationLLM-assisted modules: Context Generator, Intent Recognition, Task Planner, Modality SelectorReduces cognitive load, interprets commands accurately, provides flexible communication modes; requires further learning-based intent understanding and large-scale validation
[ 93 ]Autonomous swarm formation, safe command executionImages, textGPT-4 multimodal LLM, pre-training on single-UAVAchieves 82.7% command extraction accuracy; 83.8% formation planning success; handles ambiguous human instructions, integrates perception and swarm status
[ 57 ]Dynamic mission planning, multi-agent coordination, situational awarenessText, visual, sensor dataMLLM (Doubao 1.5 Vision Pro), chain-of-thought reasoning, multi-source data fusionAutonomous swarm management, adaptive task execution, natural language interaction; addresses hallucination and inference-latency trade-offs
[ 94 ]Cyber-physical threat detection in UAV swarmsSensor data, logs, UAV communicationsLarge multimodal models, hierarchical zero-trust architecture, edge-fog-cloud schedulingImproves robustness and timeliness in detecting threats; balances inference accuracy, latency, and computational constraints
[ 95 ]Intuitive UAV control via natural languageText, video, imageMLLMs (Gemini / LLaVA), logistic regression classifier, YOLOv10, DeepSORT, MAVSDKHigh-accuracy command execution (97.58% efficiency in video selection), effective autonomous operation, reduces need for specialized programming skills
[ 96 ]Real-time fire monitoring, automated report generationUAV imagery, ground sensors, meteorological dataLLM (DeepSeek), Grounding DINO, YOLOv8, improved A* path planningGenerates combined text-and-image reports, identifies fireground elements, optimizes evacuation routes, enhances situational awareness and operational efficiency
Table VIII : Multimodal LLM applications in UAV swarm operations, comparing frameworks for human-swarm interaction, autonomous formation, threat detection, natural language control, and emergency monitoring across diverse sensory and linguistic inputs.
ReferenceCore Innovation / FocusKey Technical ComponentsKey Outcomes / PerformanceLimitations / Challenges Addressed
[ 97 ]End-to-end VLN; reframes navigation as QA; cross-modal grounding for interpretability.Fine-tuned LLM, open-vocabulary visual perception, novel cross-modal grounding mechanism.Significant improvement in instruction-following accuracy & path efficiency; robust zero-shot generalization in diverse indoor/outdoor settings.Minimizes task-specific supervision; outperforms closed-vocabulary baselines.
[ 98 ]Integrates VLN with NMPC for safe, precise urban flight.LLM, fine-grained spatial verbalizer, history path memory, NMPC module for control optimization.Substantial improvement in navigation success rate & operational efficiency; ensures safe, constraint-aware flight.Reduces human operator cognitive load and advances explainable autonomous decision-making.
[ 99 ]Addresses out-of-distribution (OOD) instructions via an LLM-assisted Instruction Rephraser (LLMIR).Conditional Transformer (VLCT), SentenceBERT, LLM-assisted Instruction Rephraser (LLMIR).1.39% absolute improvement in task success rate; +1.51% improvement on OOD test set.Enhances reliability with vague/user instructions; improves user-friendliness.
[ 100 ]Dual-UAV collaboration at different altitudes for superior navigation.Multimodal LLM (Pilot-LLM), orthographic mapping, multi-stage pathfinding pipeline.Significantly outperforms single-UAV methods; higher success rates & better generalization on unseen environments/objects.Overcomes limitations of single-UAV perspective via collaborative reasoning.
[ 101 ]Proposes a new VLN benchmark for UAVs in continuous 3D outdoor urban spaces.Task definition for continuous, open 3D navigation with first-person visual perceptions.Introduces challenges in 3D spatial reasoning, language understanding, and cross-modal alignment.Addresses the gap in aerial-agent navigation for complex urban environments.
Table IX : Comparison of VLN frameworks for UAVs, highlighting innovations in end-to-end reasoning, safety-aware control, instruction robustness, multi-UAV collaboration, and benchmark development for continuous 3D aerial navigation.
Figure 8: Integrated high-level planning and operational intelligence pipeline for UAVs, using multimodal LLMs/VLMs to interpret instructions, infer goals, and generate flight plans, with real-time feedback loops for execution monitoring and situational awareness.
Core ChallengeSolution ApproachKey CapabilityDesired Outcome
Model uncertainty and hallucinations of foundation modelsCombining structured language reasoning with robust visual perceptionError-resilient, zero-shot task execution across diverse missionsGreater reliability and safety in real-world aerial missions
Lack of interpretability and trust in AI decisionsPairing VLM-based reasoning with real-time depth perception and operator-guided approval loopsEnhanced explainability and human-AI collaborationImproved transparency and user-aligned operation
Limited onboard computational resources for AI modelsUsing compact, finely tuned LLMs with efficient visual detection and depth estimation pipelinesHigh-level decision-making on resource-constrained UAVsWidely deployable AI-powered UAV platforms
Complex environment perception and context-aware decision-makingIntegrating domain-guided prompt execution with lightweight vision modulesSafe, context-aware decisions in dynamic environmentsIntelligent operation in complex scenarios
Human intent understanding and mission executionSystems combining language reasoning with visual perception and human-centric interactionUnderstanding human intent and complex environmentsMore intelligent, interpretable, and reliable systems
Table X : Key challenges in LLM/VLM-based UAV autonomy—including model uncertainty, interpretability, resource constraints, environmental perception, and intent understanding—paired with solution approaches, required capabilities, and desired operational outcomes.
Figure 9: Multimodal LLM/VLM framework for semantic understanding and analysis in UAV applications, integrating diverse sensor data for scene reasoning, threat assessment, and domain-specific insights.
More in this topic

Language Model-Based Control

Language model-based control uses language models to interpret goals, choose actions, and steer AI systems or physical processes.

See all 180 papers

Explore similar work

CardsList
Oct 7, 2026

LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy

Unmanned aerial vehicle (UAV) dispatch is beginning to move beyond isolated path planning and optimization-driven resource allocation toward system-level coordination supported by semantic reasoning and LLM-based interfaces. This survey provides a unified characterization of LLM-enabled UAV dispatch systems that bridges semantic intent, symbolic decision-making, and physical UAV execution. Rather than treating LLMs as standalone add-ons, we conceptualize them as a cross-layer semantic orchestration layer connecting human instructions, external solvers, and distributed control modules. We organize the literature into four representative dispatch paradigms: pipeline dispatch, global assignment dispatch, decentralized agentic dispatch, and divide-and-conquer dispatch. For each paradigm, we analyze its decision logic, system structure, control flow, representative methods, and potential LLM roles. We further examine how LLMs support semantic parsing, retrieval-grounded planning, solver orchestration, local agent reasoning, multi-agent coordination, safety assessment, and human-facing explanation. We discuss the implications of these paradigms for scalability, robustness, coordination burden, and verification requirements, and identify open challenges including latency-aware reasoning, grounding reliability, physical feasibility guarantees, edge deployment, privacy protection, and distributed consistency. This survey provides a system-level taxonomy and design perspective for integrating LLMs into safety-critical UAV dispatch systems.

Xiao Han, Aoyang Quan, Xiangyu Zhao +2

School of Computer Science, Zhejiang University of Technology, China

LLM Agent Orchestration
AskPDF
Jul 5, 2026

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

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.

Yousef Emami, Rahim Taheri, Mohammadhossein Homaei +2

Senior Member, IEEE

Multi-Agent LLM SystemsAI Agent SecurityMulti-Robot CoordinationMulti-Agent System SecurityAgentic AI
AskPDF
Apr 15, 2026

Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap

Vision-and-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) represents a pivotal challenge in embodied artificial intelligence, focused on enabling UAVs to interpret high-level human commands and execute long-horizon tasks in complex 3D environments. This paper provides a comprehensive and structured survey of the field, from its formal task definition to the current state of the art. We establish a methodological taxonomy that charts the technological evolution from early modular and deep learning approaches to contemporary agentic systems driven by large foundation models, including Vision-Language Models (VLMs), Vision-Language-Action (VLA) models, and the emerging integration of generative world models with VLA architectures for physically-grounded reasoning. The survey systematically reviews the ecosystem of essential resources simulators, datasets, and evaluation metrics that facilitates standardized research. Furthermore, we conduct a critical analysis of the primary challenges impeding real-world deployment: the simulation-to-reality gap, robust perception in dynamic outdoor settings, reasoning with linguistic ambiguity, and the efficient deployment of large models on resource-constrained hardware. By synthesizing current benchmarks and limitations, this survey concludes by proposing a forward-looking research roadmap to guide future inquiry into key frontiers such as multi-agent swarm coordination and air-ground collaborative robotics.

Hanxuan Chen, Jie Zheng, Siqi Yang +9

Autel Robotics, Shenzhen, China · School of Intelligent Software and Engineering, Nanjing University, Nanjing, China · School of Computer, Data & Information Sciences, University of Wisconsin-Madison, Madison, WI, USA +3

Vision-Language NavigationAerial VLNUAV NavigationVision-Language-Action Models
AskPDF