WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery
cs.CV
Submitted: 2026-09-25
Updated: 2026-10-06
Code: https://github.com/huggingface/trl
Terminology
Sources
- RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
- Toolformer: Language Models Can Teach Themselves to Use Tools
- RouteLLM: Learning to Route LLMs with Preference Data
- When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
- Evaluating Large Language Models with fmeval
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Subobject-level Image Tokenization
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
- ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration
- ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks
- Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search
- RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
- Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism
- OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
- A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions
- Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models