{"total":101,"rows":[{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484,"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":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"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":"2504.13055","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","created":"2025-04-17","cited_by_count":86,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2505.17018","title":"SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward","created":"2025-05-22","cited_by_count":45,"area":"lr"},{"id":"2503.16188","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","created":"2025-03-20","cited_by_count":44,"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":"2506.00711","title":"QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training","created":"2025-05-31","cited_by_count":38,"area":"lr"},{"id":"2506.18234","title":"Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning","created":"2025-06-23","cited_by_count":38,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"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":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","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":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2511.06499","title":"SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports","created":"2025-11-09","cited_by_count":17,"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":"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":"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":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2505.24173","title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?","created":"2025-05-30","cited_by_count":10,"area":"lr"},{"id":"2508.08177","title":"MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision","created":"2025-08-11","cited_by_count":10,"area":"lr"},{"id":"2509.15279","title":"Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning","created":"2025-09-18","cited_by_count":10,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2512.14157","title":"Ophiuchus: Incentivizing Tool-augmented \"Think with Images\" for Joint Medical Segmentation, Understanding and Reasoning","created":"2025-12-16","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":"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":"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":"2512.13159","title":"SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning","created":"2025-12-15","cited_by_count":8,"area":"lr"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"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":"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":"2508.19097","title":"Reasoning LLMs in the Medical Domain: A Literature Survey","created":"2025-08-26","cited_by_count":6,"area":"lr"},{"id":"2510.20967","title":"3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models","created":"2025-10-23","cited_by_count":6,"area":"lr"},{"id":"2504.00016","title":"Medical Reasoning in LLMs: An In-Depth Analysis of DeepSeek R1","created":"2025-03-27","cited_by_count":5,"area":"lr"},{"id":"2506.19469","title":"Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning","created":"2025-06-24","cited_by_count":5,"area":"lr"},{"id":"2506.23061","title":"Empowering Small VLMs to Think with Dynamic Memorization and Exploration","created":"2025-06-29","cited_by_count":5,"area":"lr"},{"id":"2508.10865","title":"Performance of GPT-5 in Brain Tumor MRI Reasoning","created":"2025-08-14","cited_by_count":5,"area":"lr"},{"id":"2509.03906","title":"Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning","created":"2025-09-04","cited_by_count":5,"area":"lr"},{"id":"2604.08203","title":"MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning","created":"2026-04-09","cited_by_count":5,"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":"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":"2507.01327","title":"Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy","created":"2025-07-02","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":"2508.11196","title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","created":"2025-08-15","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":"2601.03321","title":"HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2601.10949","title":"MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement","created":"2026-01-16","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":"2606.00440","title":"SDR: Set-Distance Rewards for Radiology Report Generation","created":"2026-05-30","cited_by_count":3,"area":"lr"},{"id":"2507.23541","title":"Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning","created":"2025-07-31","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":"2512.06835","title":"Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning","created":"2025-12-07","cited_by_count":2,"area":"lr"},{"id":"2601.01195","title":"Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering","created":"2026-01-03","cited_by_count":2,"area":"lr"},{"id":"2604.16557","title":"S-GRPO: Unified Post-Training for Large Vision-Language Models","created":"2026-04-17","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":"2505.18467","title":"Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2505.19954","title":"An Explainable Diagnostic Framework for Neurodegenerative Dementias via Reinforcement-Optimized LLM Reasoning","created":"2025-05-26","cited_by_count":1,"area":"lr"},{"id":"2509.06409","title":"Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning","created":"2025-09-08","cited_by_count":1,"area":"lr"},{"id":"2511.18084","title":"The Alignment Paradox of Medical Large Language Models in Infertility Care: Decoupling Algorithmic Improvement from Clinical Decision-making Quality","created":"2025-11-22","cited_by_count":1,"area":"lr"},{"id":"2512.03667","title":"Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoning","created":"2025-12-03","cited_by_count":1,"area":"lr"},{"id":"2601.04672","title":"Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning","created":"2026-01-08","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":"2602.07529","title":"MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution","created":"2026-02-07","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":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.18656","title":"Balanced Thinking: Improving Chain of Thought Training in Vision Language Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.03179","title":"Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models","created":"2026-04-03","cited_by_count":1,"area":"lr"},{"id":"2607.07761","title":"Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2608.08623","title":"MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning","created":"2026-08-09","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":"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":"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":"2601.14044","title":"Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2602.12164","title":"Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2602.14160","title":"Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2603.28120","title":"MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2604.08815","title":"Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language Models","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2604.28011","title":"Echo-{\\alpha}: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation","created":"2026-04-30","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":"2607.00147","title":"RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation","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":"2608.26147","title":"CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}