arXiv 2601.041182026-01-08cs.CV

GeoReason: 通过逻辑一致性强化学习对遥感视觉-语言模型中的思考与回答进行对齐

GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning

Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；Key Laboratory of Target Cognition and Application Technology, Chinese Academy of Sciences（中国科学院目标认知与应用技术重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）

Wenshuai Li, Xiantai Xiang, Zixiao Wen, Guangyao Zhou, Ben Niu, Feng Wang, Lijia Huang, Qiantong Wang, Yuxin Hu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

GeoReason通过逻辑一致性强化学习提升遥感视觉-语言模型的推理可靠性与可解释性，实现思考与决策的同步。

摘要：

遥感视觉-语言模型（RS-VLMs）的发展强调了从以感知为中心的识别向高层次演绎推理转变的重要性，以提高复杂空间任务中的认知可靠性。然而，当前模型常遭受逻辑幻觉的困扰，即正确答案来源于错误的推理链或依赖于位置捷径而非空间逻辑。这种脱节削弱了战略空间决策的可靠性。为此，我们提出了GeoReason，一个旨在同步内部思考与最终决策的框架。我们首先构建了GeoReason-Bench，一个逻辑驱动的数据集，包含4000个由几何原语和专家知识合成的推理轨迹。然后，我们制定了一种两阶段训练策略：（1）监督知识初始化，以使模型具备推理语法和领域专业知识；（2）一致性感知强化学习，以优化演绎可靠性。第二阶段整合了新的逻辑一致性奖励，通过选项排列策略惩罚逻辑漂移，将决策锚定在可验证的推理轨迹上。实验结果表明，我们的框架显著提高了RS-VLMs的认知可靠性和可解释性，相较于其他先进方法取得了最先进的性能。

英文摘要：

The evolution of Remote Sensing Vision-Language Models(RS-VLMs) emphasizes the importance of transitioning from perception-centric recognition toward high-level deductive reasoning to enhance cognitive reliability in complex spatial tasks. However, current models often suffer from logical hallucinations, where correct answers are derived from flawed reasoning chains or rely on positional shortcuts rather than spatial logic. This decoupling undermines reliability in strategic spatial decision-making. To address this, we present GeoReason, a framework designed to synchronize internal thinking with final decisions. We first construct GeoReason-Bench, a logic-driven dataset containing 4,000 reasoning trajectories synthesized from geometric primitives and expert knowledge. We then formulate a two-stage training strategy: (1) Supervised Knowledge Initialization to equip the model with reasoning syntax and domain expertise, and (2) Consistency-Aware Reinforcement Learning to refine deductive reliability. This second stage integrates a novel Logical Consistency Reward, which penalizes logical drift via an option permutation strategy to anchor decisions in verifiable reasoning traces. Experimental results demonstrate that our framework significantly enhances the cognitive reliability and interpretability of RS-VLMs, achieving state-of-the-art performance compared to other advanced methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。