{"total":97,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2506.07044","title":"Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning","created":"2025-06-08","cited_by_count":230,"area":"lr"},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2503.13939","title":"Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models","created":"2025-03-18","cited_by_count":144,"area":"lr"},{"id":"2503.20752","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models","created":"2025-03-26","cited_by_count":99,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2505.11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","created":"2025-05-16","cited_by_count":40,"area":"lr"},{"id":"2506.00555","title":"MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning","created":"2025-05-31","cited_by_count":40,"area":"lr"},{"id":"2506.00711","title":"QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training","created":"2025-05-31","cited_by_count":38,"area":"lr"},{"id":"2505.17952","title":"Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL","created":"2025-05-23","cited_by_count":36,"area":"lr"},{"id":"2505.16964","title":"MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning","created":"2025-05-22","cited_by_count":34,"area":"lr"},{"id":"2504.20930","title":"ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification","created":"2025-04-29","cited_by_count":31,"area":"lr"},{"id":"2505.03981","title":"X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains","created":"2025-05-06","cited_by_count":31,"area":"lr"},{"id":"2508.02669","title":"MedVLThinker: Simple Baselines for Multimodal Medical Reasoning","created":"2025-08-04","cited_by_count":27,"area":"lr"},{"id":"2508.06206","title":"Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model","created":"2025-08-08","cited_by_count":23,"area":"lr"},{"id":"2505.17659","title":"Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2508.08039","title":"Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning","created":"2025-08-11","cited_by_count":19,"area":"lr"},{"id":"2510.11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment","created":"2025-10-13","cited_by_count":18,"area":"lr"},{"id":"2505.19213","title":"Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning","created":"2025-05-25","cited_by_count":16,"area":"lr"},{"id":"2506.16962","title":"Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search","created":"2025-06-20","cited_by_count":16,"area":"lr"},{"id":"2504.03724","title":"CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward","created":"2025-03-31","cited_by_count":15,"area":"lr"},{"id":"2506.09790","title":"ComfyUI-R1: Exploring Reasoning Models for Workflow Generation","created":"2025-06-11","cited_by_count":15,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2505.24105","title":"Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2506.05384","title":"Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment","created":"2025-06-03","cited_by_count":14,"area":"lr"},{"id":"2510.10052","title":"Think Twice to See More: Iterative Visual Reasoning in Medical VLMs","created":"2025-10-11","cited_by_count":13,"area":"lr"},{"id":"2506.03097","title":"EgoVLM: Policy Optimization for Egocentric Video Understanding","created":"2025-06-03","cited_by_count":12,"area":"lr"},{"id":"2508.00669","title":"Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications","created":"2025-08-01","cited_by_count":10,"area":"lr"},{"id":"2511.23269","title":"OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2506.06600","title":"RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints","created":"2025-06-07","cited_by_count":9,"area":"lr"},{"id":"2506.07045","title":"Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs","created":"2025-06-08","cited_by_count":9,"area":"lr"},{"id":"2506.10353","title":"Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding","created":"2025-06-12","cited_by_count":9,"area":"lr"},{"id":"2504.09258","title":"PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks","created":"2025-04-12","cited_by_count":8,"area":"lr"},{"id":"2505.11872","title":"PRS-Med: Position Reasoning Segmentation in Medical Imaging","created":"2025-05-17","cited_by_count":8,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2506.17939","title":"GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning","created":"2025-06-22","cited_by_count":8,"area":"lr"},{"id":"2508.20549","title":"MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning","created":"2025-08-28","cited_by_count":8,"area":"lr"},{"id":"2506.18512","title":"MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2510.21324","title":"CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation","created":"2025-10-24","cited_by_count":7,"area":"lr"},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2603.06570","title":"SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning","created":"2026-03-06","cited_by_count":7,"area":"lr"},{"id":"2505.23118","title":"Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2508.16129","title":"Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2603.06366","title":"OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis","created":"2026-03-06","cited_by_count":6,"area":"lr"},{"id":"2506.16796","title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","created":"2025-06-20","cited_by_count":5,"area":"lr"},{"id":"2506.06856","title":"Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning","created":"2025-06-07","cited_by_count":4,"area":"lr"},{"id":"2508.12957","title":"Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation","created":"2025-08-18","cited_by_count":4,"area":"lr"},{"id":"2510.04225","title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2602.01200","title":"Med3D-R1: Incentivizing Clinical Reasoning in 3D Medical Vision-Language Models for Abnormality Diagnosis","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2603.01607","title":"CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2506.13102","title":"Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2508.03733","title":"CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning","created":"2025-07-31","cited_by_count":3,"area":"lr"},{"id":"2508.10967","title":"Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2510.19626","title":"MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom","created":"2025-10-22","cited_by_count":3,"area":"lr"},{"id":"2603.01301","title":"When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2603.05867","title":"TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis","created":"2026-03-06","cited_by_count":3,"area":"lr"},{"id":"2603.13800","title":"Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space","created":"2026-03-14","cited_by_count":3,"area":"lr"},{"id":"2606.00440","title":"SDR: Set-Distance Rewards for Radiology Report Generation","created":"2026-05-30","cited_by_count":3,"area":"lr"},{"id":"2505.23867","title":"InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2510.18303","title":"Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2601.07695","title":"Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model","created":"2026-01-12","cited_by_count":2,"area":"lr"},{"id":"2603.12430","title":"Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2605.20277","title":"Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2607.16303","title":"Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2504.02885","title":"Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation","created":"2025-04-02","cited_by_count":1,"area":"lr"},{"id":"2505.18467","title":"Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2511.12861","title":"From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2512.19512","title":"Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation","created":"2025-12-22","cited_by_count":1,"area":"lr"},{"id":"2601.08440","title":"Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosis","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2602.00400","title":"KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQA","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.10619","title":"Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2604.09757","title":"MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2605.15574","title":"MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.28388","title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2503.23130","title":"Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery","created":"2025-03-29","cited_by_count":0,"area":"lr"},{"id":"2508.08688","title":"STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2509.22283","title":"Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2509.24231","title":"EVLF-FM: Explainable Vision Language Foundation Model for Medicine","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2512.11060","title":"Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2512.17213","title":"CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2512.19317","title":"SafeMed-R1: Adversarial Reinforcement Learning for Generalizable and Robust Medical Reasoning in Vision-Language Models","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2512.23090","title":"Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients","created":"2025-12-28","cited_by_count":0,"area":"lr"},{"id":"2601.06054","title":"A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2601.14044","title":"Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2603.29608","title":"Learning Diagnostic Reasoning for Decision Support in Toxicology","created":"2026-03-31","cited_by_count":0,"area":"lr"},{"id":"2606.05174","title":"Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2606.25894","title":"Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2606.28164","title":"EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2606.31599","title":"Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2608.10964","title":"CARE: Confidence-Aware Reasoning for Reliable Medical VQA","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.17607","title":"PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.26147","title":"CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}