Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

arXiv:2609.01404 · cs.RO, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-01

Updated: 2026-10-15

Comments: Preprint

Code: https://github.com/naver-ai/DroneCATS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Action Space — 11× in this paper · explained in 1 episode
• Grounding — 10× in this paper · explained in 3 episodes
• Trace — 8× in this paper · explained in 2 episodes
• Verifier — 7× in this paper · explained in 2 episodes
• Decode — 5× in this paper · explained in 2 episodes
• Failure Modes — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Affordance — 2× in this paper · explained in 1 episode
• Closed-Loop Control — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Failure Taxonomy — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Model-Agnostic — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen3-VL Technical Report
• Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
• AirHunt: Bridging VLM Semantics and Continuous Planning for Efficient Aerial Object Navigation
• DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking
• Taking Flight with Dialogue: Enabling Natural Language Control for PX4-based Drone Agent
• CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs
• Cosmos 3: Omnimodal World Models for Physical AI
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms
• Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
• ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
• UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
• ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception
• OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies