mlsanityData to 14 Oct 2026

GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning

arXiv 2509.25026 ↗First posted 29 Sep 2025cs.CVcited by 15

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Recent advances in reinforcement learning (RL) have delivered strong reasoning capabilities in natural image domains, yet their potential for Earth Observation (EO) remains largely unexplored. EO tasks introduce unique challenges, spanning referred object detection, image or region captioning, change detection, grounding, and temporal analysis, that demand task aware reasoning. We propose a novel post training framework that incorporates task aware rewards to enable effective adaptation of reasoning based RL models to diverse EO tasks. This training strategy enhances reasoning capabilities for remote sensing images, stabilizes optimization, and improves robustness. Extensive experiments across multiple EO benchmarks show consistent performance gains over state of the art generic and specialized vision language models. Code and models will be released publicly at https://mustansarfiaz.github.io/GeoVLM-R1/ .

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 43 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

27 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning15 Aug

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  8. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  9. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 526
  10. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 248
  11. 2025SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Modelscited by 212
  12. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmarkcited by 207
14 more
  1. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Modelcited by 138
  2. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cyclescited by 124
  3. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Modelcited by 113
  4. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understandingcited by 104
  5. 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Modelscited by 99
  6. 2025Reward Shaping to Mitigate Reward Hacking in RLHFcited by 88
  7. 2023Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignmentcited by 71
  8. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learningcited by 71
  9. 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
  10. 2025GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensingcited by 57
  11. 2025EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLMcited by 18
  12. 2024Demonstrating and Reducing Shortcuts in Vision-Language Representation Learningcited by 14
  13. 2025See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMscited by 7
  14. 2024Made to Order: Discovering monotonic temporal changes via self-supervised video orderingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 13.

15 papers.

Sort:

By area:

  1. 2025GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenescited by 14
  2. 2026RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoningcited by 8
  3. 2026RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMscited by 8
  4. 2026GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervisioncited by 2
  5. 2026RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observationcited by 2
  6. 2026RemoteZero: Geospatial Reasoning with Zero Labelscited by 2
  7. 2026A Training-Free Guess What Vision Language Model from Snippets to Open-Vocabulary Object Detectioncited by 1
  8. 2026Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensingcited by 1
  9. 2026GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervisioncited by 1
  10. 2025An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domaincited by 0
  11. 2026Earth Science Foundation Models: From Perception to Reasoning and Discoverycited by 0
  12. 2026GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Imagescited by 0
3 more
  1. 2026Diagnosing Aerial-View Object Detectors with Foundational Image Generative Modelscited by 0
  2. 2026More with Less: a Large Scale Remote Sensing VLM with a Simple Recipecited by 0
  3. 2026PoE-Fuse: Precision-Weighted Expert Fusion for Bi-Temporal Change Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Few-Shot Vision-Language Reasoning for Satellite Imagery via Verifiable Rewards
  2. 2025RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow
  3. 2026GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning
  4. 2025Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing
  5. 2025Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
  6. 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
  7. 2025GRASP: Geospatial pixel Reasoning viA Structured Policy learning
  8. 2026LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning