X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

arXiv:2610.16811 · cs.CV · Submitted 2026-10-12 · Read on arXiv

cs.CV

Submitted: 2026-10-12

Updated: 2026-10-12

Code: https://github.com/DIAGNijmegen/opencxr

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Qwen3-VL Technical Report
• RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
• Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
• PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
• Automated Cardiothoracic Ratio Calculation and Cardiomegaly Detection using Deep Learning Approach
• Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
• Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors
• A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
• Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
• ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
• Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning
• Uncertainty Modeling for Out-of-Distribution Generalization
• GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision
• STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
• FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
• Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
• AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
• Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

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