# WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding arXiv: https://arxiv.org/abs/2607.10120 ยท HTML: https://mlsanity.com/paper/2607.10120/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 34 of its 69 references that are in the map. - First posted on arXiv 11 Jul 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, 30 of 34) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024) - [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024) - [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023) - [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024) - [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024) - [GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing](https://mlsanity.com/paper/2501.13925/) (2025) - [GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution](https://mlsanity.com/paper/2505.21375/) (2025) - [When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning](https://mlsanity.com/paper/2503.07588/) (2025) - [Large Language Models for Captioning and Retrieving Remote Sensing Images](https://mlsanity.com/paper/2402.06475/) (2024) - [RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts](https://mlsanity.com/paper/2412.05679/) (2024) - [Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)](https://mlsanity.com/paper/2503.11070/) (2025) - [ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks](https://mlsanity.com/paper/2511.12267/) (2025) - [Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2509.21976/) (2025) - [Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models](https://mlsanity.com/paper/2509.22221/) (2025) - [GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes](https://mlsanity.com/paper/2511.22645/) (2025) - [Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search](https://mlsanity.com/paper/2511.20460/) (2025) - [A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs](https://mlsanity.com/paper/2512.17319/) (2025) - [GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing](https://mlsanity.com/paper/2501.06828/) (2025) - [GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2602.14201/) (2026) - [RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs](https://mlsanity.com/paper/2604.07765/) (2026) - [ProVG: Progressive Visual Grounding via Language Decoupling for Remote Sensing Imagery](https://mlsanity.com/paper/2604.01893/) (2026) - [Asking like Socrates: Socrates helps VLMs understand remote sensing images](https://mlsanity.com/paper/2511.22396/) (2025) - [Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing](https://mlsanity.com/paper/2512.19302/) (2025) - [F2Net: A Frequency-Fused Network for Ultra-High Resolution Remote Sensing Segmentation](https://mlsanity.com/paper/2506.07847/) (2025) - [GRASP: Geospatial pixel Reasoning viA Structured Policy learning](https://mlsanity.com/paper/2508.17102/) (2025) - [GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding](https://mlsanity.com/paper/2512.02715/) (2025) ## Built on by (most cited first, 2 of 2) - [The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding](https://mlsanity.com/paper/2609.31747/) (2026) - [RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA](https://mlsanity.com/paper/2609.38072/) (2026) ## Abstract (arXiv) Ultra-High-Resolution (UHR) remote sensing image understanding requires Vision-Language Models (VLMs) to capture both the global scene layout and sparse yet task-critical local details under limited computational budgets. Existing methods mainly follow two paradigms. One is passive perception, which relies on resolution expansion or token compression and may therefore discard fine-grained details. The other is active perception, which depends on multi-round zooming and search, but suffers from high latency, contextual fragmentation, and error accumulation. We argue that a more effective path toward UHR understanding lies not in accessing more, but in organizing better. To this end, we propose WeaveEarth, a training-free framework that reformulates UHR understanding as a problem of structured evidence construction and reasoning under global context constraints. Specifically, WeaveEarth first employs Global-Aware Evidence Construction to select a compact, low-redundancy, and spatially complementary Minimal Support Evidence Set. It then introduces Structured Evidence Reasoning, which weaves local evidence, spatial metadata, and relative topology into a unified reasoning interface, thereby enhancing the VLM's ability to perform global-local joint reasoning. Extensive experiments show that WeaveEarth consistently outperforms strong baselines and existing UHR methods across multiple UHR remote sensing benchmarks and multiple frozen VLM backbones. Code is available at https://github.com/XianZhi-Ma/WeaveEarth.