{"total":173,"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":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98,"area":null},{"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":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"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":"2505.19630","title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","created":"2025-05-26","cited_by_count":27,"area":"agents"},{"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":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"area":null},{"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":"2509.09254","title":"Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis","created":"2025-09-11","cited_by_count":18,"area":"mllm"},{"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":"2602.06965","title":"MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images","created":"2026-02-06","cited_by_count":15,"area":"mllm"},{"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":"2508.01617","title":"LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding","created":"2025-08-03","cited_by_count":13,"area":"mllm"},{"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":"2604.26283","title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","created":"2026-04-29","cited_by_count":12,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2511.22055","title":"OralGPT-Omni: A Versatile Dental Multimodal Large Language Model","created":"2025-11-27","cited_by_count":11,"area":"mllm"},{"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":"2602.16110","title":"OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis","created":"2026-02-18","cited_by_count":10,"area":null},{"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":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2509.20146","title":"EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models","created":"2025-09-24","cited_by_count":9,"area":"mllm"},{"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":"2505.02830","title":"AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation","created":"2025-05-05","cited_by_count":8,"area":null},{"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":"2511.00846","title":"OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks","created":"2025-11-02","cited_by_count":8,"area":"mllm"},{"id":"2602.03320","title":"MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"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":"2509.06467","title":"Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration","created":"2025-09-08","cited_by_count":7,"area":null},{"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":"2602.23363","title":"MediX-R1: Open Ended Medical Reinforcement Learning","created":"2026-02-26","cited_by_count":7,"area":"mllm"},{"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":"2602.12705","title":"MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs","created":"2026-02-13","cited_by_count":6,"area":"mllm"},{"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":"2603.25155","title":"Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models","created":"2026-03-26","cited_by_count":6,"area":"mllm"},{"id":"2604.14475","title":"Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve","created":"2026-04-15","cited_by_count":6,"area":"agents"},{"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":"2506.21355","title":"SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2601.06847","title":"MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data","created":"2026-01-11","cited_by_count":5,"area":"mllm"},{"id":"2603.07562","title":"Brain-WM: Brain Glioblastoma World Model","created":"2026-03-08","cited_by_count":5,"area":"wm"},{"id":"2603.24649","title":"MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows","created":"2026-03-25","cited_by_count":5,"area":null},{"id":"2505.20573","title":"Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners","created":"2025-05-26","cited_by_count":4,"area":null},{"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":"2508.03734","title":"A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models","created":"2025-07-31","cited_by_count":4,"area":null},{"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":"2512.10691","title":"Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning","created":"2025-12-11","cited_by_count":4,"area":"mllm"},{"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":"2604.09450","title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2606.19950","title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","created":"2026-06-18","cited_by_count":4,"area":"mllm"},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2506.05831","title":"HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding","created":"2025-06-06","cited_by_count":3,"area":null},{"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":"2507.11200","title":"How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study","created":"2025-07-15","cited_by_count":3,"area":"mllm"},{"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":"2509.22404","title":"RAU: Reference-based Anatomical Understanding with Vision Language Models","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"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":"2512.04238","title":"6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models","created":"2025-12-03","cited_by_count":3,"area":"mllm"},{"id":"2601.02737","title":"Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench","created":"2026-01-06","cited_by_count":3,"area":"mllm"},{"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":"2605.27378","title":"OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis","created":"2026-04-09","cited_by_count":3,"area":null},{"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"}],"next_cursor":"100"}