Abstract
Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, , we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,000 question-answer pairs with an average length of 71 words, spanning 14 tasks and up to eight temporal phases. VLRS-Bench is constructed via a specialized pipeline that integrates RS-specific priors and expert knowledge to ensure geospatial realism and reasoning complexity. Experimental results reveal significant bottlenecks in existing state-of-the-art MLLMs, providing critical insights for advancing multimodal reasoning within the remote sensing community.
Abstract (translated)
最近的多模态大型语言模型（MLLMs）进展使得复杂推理成为可能。然而，现有的遥感（RS）基准测试仍然偏向于感知任务，例如物体识别和场景分类。这种限制阻碍了MLLMs在认知要求高的RS应用中的发展。为了解决这个问题，我们提出了一个视觉语言推理基准（VLRS-Bench），这是首个专门针对复杂RS推理的基准。VLRS-Bench涵盖了认知、决策和预测三个核心维度，包含2,000个问题-答案对，平均长度为71个单词，并涵盖14项任务及多达八个时间阶段。通过一个整合了遥感特定先验知识和专家知识的专业化管道构建而成的VLRS-Bench确保了地理空间的真实性以及推理复杂性。实验结果显示现有最先进的MLLMs存在显著瓶颈，这为推进多模态推理在遥感领域的进步提供了关键见解。
URL
https://arxiv.org/abs/2602.07045
