We present QuadAgent, a training-free agent system for agile quadrotor flight guided by vision-language inputs. Unlike prior end-to-end or serial agent approaches, QuadAgent decouples high-level reasoning from low-level control using an asynchronous multi-agent architecture: Foreground Workflow Agents handle active tasks and user commands, while Background Agents perform look-ahead reasoning. The system maintains scene memory via the Impression Graph, a lightweight topological map built from sparse keyframes, and ensures safe flight with a vision-based obstacle avoidance network. Simulation results show that QuadAgent outperforms baseline methods in efficiency and responsiveness. Real-world experiments demonstrate that it can interpret complex instructions, reason about its surroundings, and navigate cluttered indoor spaces at speeds up to 5 m/s.
@article{arxiv.2604.02786,
title = {QuadAgent: A Responsive Agent System for Vision-Language Guided Quadrotor Agile Flight},
author = {Ao Zhuang and Feng Yu and Tianbao Zhang and Linzuo Zhang and Danping Zou},
journal= {arXiv preprint arXiv:2604.02786},
year = {2026}
}