GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917188948983808 |
|---|---|
| author | Li, Wenshuai Xiang, Xiantai Wen, Zixiao Zhou, Guangyao Niu, Ben Wang, Feng Huang, Lijia Wang, Qiantong Hu, Yuxin |
| author_facet | Li, Wenshuai Xiang, Xiantai Wen, Zixiao Zhou, Guangyao Niu, Ben Wang, Feng Huang, Lijia Wang, Qiantong Hu, Yuxin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04118 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning Li, Wenshuai Xiang, Xiantai Wen, Zixiao Zhou, Guangyao Niu, Ben Wang, Feng Huang, Lijia Wang, Qiantong Hu, Yuxin Computer Vision and Pattern Recognition 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. |
| title | GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.04118 |