Metraipolis › archive › dc_7963b377afbd
Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System — arXiv:2608.11738
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11738
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:16:09.538Z
- SHA-256 of the archived text
b65292dc12347468b12a4769736e37cb8fbb9e81403616f6348be40b3e5667c3- Stable URL of this page
https://metraipolis.com/documento/dc_7963b377afbd
How to cite
Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System — arXiv:2608.11738 — arXiv (en), https://arxiv.org/abs/2608.11738 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7963b377afbd (Metraipolis archive dc_7963b377afbd, sha256 b65292dc12347468b12a4769736e37cb8fbb9e81403616f6348be40b3e5667c3)
BibTeX
@misc{dc7963b377afbd,
title = {Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System — arXiv:2608.11738},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11738},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7963b377afbd; sha256 b65292dc12347468b12a4769736e37cb8fbb9e81403616f6348be40b3e5667c3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11738. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal Large Language Model (MLLM)-based UAV aerial image understanding and reasoning is essential for aerial intelligence yet poses distinct challenges arising from extreme scale variation, arbitrary camera orientations, and high object density. Despite growing interest, existing evaluations remain fragmented across individual datasets and narrow tasks, leaving a critical gap in unified assessment of UAV understanding and reasoning capabilities. To fill this gap, we construct UAVQA-Bench, a benchmark of 1,500 human-annotated QA pairs drawn from 13 public UAV datasets, covering 6 capability dimensions and 16 tasks in both multiple-choice and visual grounding formats. Systematic evaluation of a broad range of open-source and closed-source MLLMs as well as agent-based systems on UAVQA-Bench identifies three key failure modes: domain-toolset mismatch, unchecked error propagation, and static reasoning. Motivated by these findings, we propose UAV-MAS, a training-free multi-agent system for MLLM-based UAV aerial image understanding and reasoning, comprising a Domain-Specific Perception Engine (DSPE) that routes queries to task-appropriate visual tools, a Context-Aware Iterative Refinement module (CAIR) that validates intermediate reasoning to curb error accumulation, and a Difficulty-Aware Adaptive Search mechanism (DAAS) that adjusts search depth to question difficulty. UAV-MAS with a 32B open-source MLLM achieves 77.0% overall accuracy on UAVQA-Bench, surpassing Gemini 3 Pro by 4.0\%, while the 8B variant improves 8.7\% over its base model. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.11738 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:08:46.725Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).