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

arXiv: https://arxiv.org/abs/2601.04118 · HTML: https://mlsanity.com/paper/2601.04118/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model](https://mlsanity.com/paper/2401.09712/) (2024)
- [SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding](https://mlsanity.com/paper/2406.10100/) (2024)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning](https://mlsanity.com/paper/2506.16141/) (2025)
- [Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning](https://mlsanity.com/paper/2506.10521/) (2025)
- [Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models](https://mlsanity.com/paper/2501.18533/) (2025)
- [RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering](https://mlsanity.com/paper/2411.01595/) (2024)
- [Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models](https://mlsanity.com/paper/2503.00743/) (2025)
- [Asking like Socrates: Socrates helps VLMs understand remote sensing images](https://mlsanity.com/paper/2511.22396/) (2025)
- [SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection](https://mlsanity.com/paper/2601.02249/) (2026)
- [D3R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images](https://mlsanity.com/paper/2601.02747/) (2026)

## Built on by (most cited first, 10 of 10)

- [RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs](https://mlsanity.com/paper/2604.07765/) (2026)
- [OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs](https://mlsanity.com/paper/2603.11804/) (2026)
- [RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation](https://mlsanity.com/paper/2604.17243/) (2026)
- [RemoteZero: Geospatial Reasoning with Zero Labels](https://mlsanity.com/paper/2605.04451/) (2026)
- [Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs](https://mlsanity.com/paper/2606.20177/) (2026)
- [Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing](https://mlsanity.com/paper/2601.17673/) (2026)
- [RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding](https://mlsanity.com/paper/2604.17504/) (2026)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)
- [GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence](https://mlsanity.com/paper/2606.17246/) (2026)
- [LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning](https://mlsanity.com/paper/2608.13344/) (2026)

## Abstract (arXiv)

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.