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

TL;DR

UAV-CodeAgents introduces a scalable multi-agent framework utilizing large language and vision-language models for autonomous UAV mission planning, enabling precise target localization and dynamic environment adaptation with high success rates.

Contribution

The paper presents a novel multi-agent system combining ReAct paradigm and vision-language reasoning for UAV mission planning, including a new pixel-pointing mechanism and a benchmark dataset.

Findings

Higher reliability at lower decoding temperature (0.5)

Average mission creation time of 96.96 seconds

Success rate of 93% in large-scale scenarios

Abstract

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.