Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing

• URL: http://arxiv.org/abs/2607.25993v1
• Date: Tue, 28 Jul 2026 17:09:16 GMT
• Title: Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing
• Abstract summary: We introduce GeoMTVR, a large-scale Multi-Tool Visual Reasoning dataset built from wide-area satellite imagery.<n>By combining SFT on GeoMTVR with our RL algorithm, we develop GeoLens, a multi-tool visual reasoning MLLM for UHR RS.<n>Experiments show that GeoLens consistently outperforms direct reasoning and single-tool zoom-in baselines.
• Score: 24.62771308673739
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental challenge for multimodal large language models (MLLMs): task-relevant evidence is often sparse, local, and spatially dispersed across extremely large visual contexts. A natural solution is to equip MLLMs with zoom-in tools for active local inspection. However, through a pilot study on XLRS-Bench, we find that zoom-in is only partially effective: it resolves easy and medium-level tasks with locally recoverable evidence, but saturates on hard cases requiring global search, multi-region comparison, path planning, or dispersed-evidence reasoning. Motivated by this finding, we move beyond single-tool zoom-in and introduce GeoMTVR, a large-scale Geospatial Multi-Tool Visual Reasoning dataset built from wide-area satellite imagery. GeoMTVR contains 13K UHR VQA samples with interleaved reasoning trajectories, diverse visual tool calls, and returned visual observations, enabling models to learn question decomposition, tool selection, regional inspection, object-level grounding, auxiliary visual reasoning, and cross-tool evidence integration. Beyond supervised fine-tuning, we propose a tool-attention-focused reinforcement learning algorithm that concentrates optimization on critical tool-use decisions, including when to invoke tools, which tool to select, where to apply it, and how to interpret tool outputs. By combining SFT on GeoMTVR with our RL algorithm, we develop GeoLens, a multi-tool visual reasoning MLLM for UHR RS. Experiments show that GeoLens consistently outperforms direct reasoning and single-tool zoom-in baselines, achieving stronger accuracy, better evidence grounding, and more efficient tool-use trajectories.

Related papers

• GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision [12.717046652815027]
  High-resolution remote sensing images usually cover large-scale scenes, where targets are often extremely small and surrounded by numerous visually similar distractors.<n>Existing MLLM-based methods usually formulate RSVG as one-step coordinate generation, which may lead to unstable predictions for small-object localization and complex queries.<n>We propose GeoSearcher, which reformulates RSVG as an anchor-guided progressive reasoning process and realizes it through two coupled stages.<n>In ACR-SFT, anchor-centric reasoning data are used to teach the model to represent key visual clues as anchors and progressively integrate location, relational, and attribute
  arXiv  Detail & Related papers  (2026-07-01T15:12:51Z)
• GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding [13.76788623862368]
  Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes.<n>Existing vision-language models can inspect local regions with zooming and cropping tools, but most exploration strategies follow either a one-shot focus or a single sequential trajectory.<n>We propose GeoVista, a planning-driven active perception framework for UHR remote sensing interpretation.
  arXiv  Detail & Related papers  (2026-05-14T07:15:46Z)
• GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery [69.05066425853326]
  "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools.<n>This is essential for ultra-high-resolution (UHR) remote sensing VQA, where task-relevant cues are sparse and tiny.<n>We propose GeoEyes, a training framework consisting of (1) a cold-start SFT dataset, UHR Chain-of-Zoom (UHR-CoZ), which covers diverse zooming regimes, and (2) an agentic reinforcement learning method, AdaZoom-GRPO, that explicitly rewards evidence gain and answer improvement during zoom
  arXiv  Detail & Related papers  (2026-02-15T15:50:55Z)
• ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization [62.03035862528452]
  ForgeryVCR is a framework that materializes imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning.<n>ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks.
  arXiv  Detail & Related papers  (2026-02-15T11:14:47Z)
• GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization [53.080882980294795]
  Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools.<n>In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses.<n>Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench.<n>We propose GeoVista, an agentic model that seamlessly integrates tool invocation within the reasoning loop, including an image-zoom-in tool to magnify regions of interest and a web-search tool to retrieve related
  arXiv  Detail & Related papers  (2025-11-19T18:59:22Z)
• ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks [49.99788276124186]
  Existing dynamic resolution and token pruning methods are constrained by a passive perception paradigm.<n>We present LRS-GRO, a large-scale benchmark dataset tailored for active perception in UHR RS processing.<n>We propose ZoomEarth, an adaptive cropping-zooming framework with a novel Region-Guided reward that provides fine-grained guidance.
  arXiv  Detail & Related papers  (2025-11-15T15:47:46Z)
• MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection [12.838872442435527]
  Small object detection in UAV imagery is crucial for applications such as search-and-rescue, traffic monitoring, and environmental surveillance.<n>Existing multi-scale fusion methods help, but add computational burden and blur fine details.<n>We propose a unified fusion framework that tightly couples global context with local detail to boost detection performance.
  arXiv  Detail & Related papers  (2025-06-15T02:54:25Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• RS-Mamba for Large Remote Sensing Image Dense Prediction [58.12667617617306]
  We propose the Remote Sensing Mamba (RSM) for dense prediction tasks in large VHR remote sensing images. RSM is specifically designed to capture the global context of remote sensing images with linear complexity. Our model achieves better efficiency and accuracy than transformer-based models on large remote sensing images.
  arXiv  Detail & Related papers  (2024-04-03T12:06:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.