# UAV-CodeAgents: Scalable UAV Mission Planning via Multi-Agent ReAct and Vision-Language Reasoning

arXiv: https://arxiv.org/abs/2505.07236 · HTML: https://mlsanity.com/paper/2505.07236/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [AerialVLN: Vision-and-Language Navigation for UAVs](https://mlsanity.com/paper/2308.06735/) (2023)
- [Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology](https://mlsanity.com/paper/2410.07087/) (2024)
- [Aerial Vision-and-Dialog Navigation](https://mlsanity.com/paper/2205.12219/) (2022)
- [UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation](https://mlsanity.com/paper/2501.05014/) (2025)
- [RaceVLA: VLA-based Racing Drone Navigation with Human-like Behaviour](https://mlsanity.com/paper/2503.02572/) (2025)
- [CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs](https://mlsanity.com/paper/2503.01378/) (2025)
- [Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation](https://mlsanity.com/paper/2410.08500/) (2024)
- [Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Design](https://mlsanity.com/paper/2312.01059/) (2023)
- [WildfireGPT: Tailored Large Language Model for Wildfire Analysis](https://mlsanity.com/paper/2402.07877/) (2024)
- [FlockGPT: Guiding UAV Flocking with Linguistic Orchestration](https://mlsanity.com/paper/2405.05872/) (2024)
- [UAV-VLRR: Vision-Language Informed NMPC for Rapid Response in UAV Search and Rescue](https://mlsanity.com/paper/2503.02465/) (2025)
- [FlightAR: AR Flight Assistance Interface with Multiple Video Streams and Object Detection Aimed at Immersive Drone Control](https://mlsanity.com/paper/2410.16943/) (2024)
- [UAV-VLPA*: A Vision-Language-Path-Action System for Optimal Route Generation on a Large Scales](https://mlsanity.com/paper/2503.02454/) (2025)
- [MorphoNavi: Aerial-Ground Robot Navigation with Object Oriented Mapping in Digital Twin](https://mlsanity.com/paper/2504.16914/) (2025)

## Built on by (most cited first, 7 of 7)

- [UAVs Meet Agentic AI: A Multidomain Survey of Autonomous Aerial Intelligence and Agentic UAVs](https://mlsanity.com/paper/2506.08045/) (2025)
- [Agentic UAVs: LLM-Driven Autonomy with Integrated Tool-Calling and Cognitive Reasoning](https://mlsanity.com/paper/2509.13352/) (2025)
- [Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems](https://mlsanity.com/paper/2601.01891/) (2026)
- [From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications](https://mlsanity.com/paper/2505.22311/) (2025)
- [MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning](https://mlsanity.com/paper/2606.31073/) (2026)
- [Leveraging Large Vision Model for Multi-UAV Co-perception in Low-Altitude Wireless Networks](https://mlsanity.com/paper/2603.16927/) (2026)
- [PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs](https://mlsanity.com/paper/2606.00104/) (2026)

## Abstract (arXiv)

We present UAV-CodeAgents, a scalable multi-agent framework for autonomous UAV mission generation, built on large language and vision-language models (LLMs/VLMs). The system leverages the ReAct (Reason + Act) paradigm to interpret satellite imagery, ground high-level natural language instructions, and collaboratively generate UAV trajectories with minimal human supervision. A core component is a vision-grounded, pixel-pointing mechanism that enables precise localization of semantic targets on aerial maps. To support real-time adaptability, we introduce a reactive thinking loop, allowing agents to iteratively reflect on observations, revise mission goals, and coordinate dynamically in evolving environments. UAV-CodeAgents is evaluated on large-scale mission scenarios involving industrial and environmental fire detection. Our results show that a lower decoding temperature (0.5) yields higher planning reliability and reduced execution time, with an average mission creation time of 96.96 seconds and a success rate of 93%. We further fine-tune Qwen2.5VL-7B on 9,000 annotated satellite images, achieving strong spatial grounding across diverse visual categories. To foster reproducibility and future research, we will release the full codebase and a novel benchmark dataset for vision-language-based UAV planning.