{"total":51,"rows":[{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526,"area":"lr"},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255,"area":"lr"},{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"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":"2505.21500","title":"ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models","created":"2025-05-27","cited_by_count":118,"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":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86,"area":"lr"},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"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":"2506.00555","title":"MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning","created":"2025-05-31","cited_by_count":40,"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":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2505.04623","title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning","created":"2025-05-07","cited_by_count":29,"area":"lr"},{"id":"2506.07905","title":"WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning","created":"2025-06-09","cited_by_count":21,"area":"lr"},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21,"area":"lr"},{"id":"2505.08364","title":"Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation","created":"2025-05-13","cited_by_count":20,"area":"lr"},{"id":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2509.25026","title":"GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning","created":"2025-09-29","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":"2506.10116","title":"ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering","created":"2025-06-11","cited_by_count":13,"area":"lr"},{"id":"2507.23581","title":"GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning","created":"2025-07-31","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2507.00748","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","created":"2025-07-01","cited_by_count":11,"area":"lr"},{"id":"2506.00568","title":"CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning","created":"2025-05-31","cited_by_count":8,"area":"lr"},{"id":"2506.03596","title":"ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning","created":"2025-06-04","cited_by_count":8,"area":"lr"},{"id":"2507.16518","title":"SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning","created":"2025-07-22","cited_by_count":8,"area":"lr"},{"id":"2505.13261","title":"Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning","created":"2025-05-19","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":"2503.09158","title":"FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2510.02752","title":"The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2601.00388","title":"Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach","created":"2026-01-01","cited_by_count":6,"area":"lr"},{"id":"2601.04442","title":"Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization","created":"2026-01-07","cited_by_count":6,"area":"lr"},{"id":"2512.06258","title":"Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs","created":"2025-12-06","cited_by_count":5,"area":"lr"},{"id":"2507.00045","title":"CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning","created":"2025-06-23","cited_by_count":4,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","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":"2602.12395","title":"What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2606.23557","title":"Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views","created":"2026-06-22","cited_by_count":3,"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":"2605.09188","title":"DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2601.17006","title":"MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2602.10019","title":"ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning","created":"2026-02-10","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":"2608.17253","title":"Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL","created":"2026-08-18","cited_by_count":1,"area":"lr"},{"id":"2602.19974","title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2605.17037","title":"D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning","created":"2026-05-16","cited_by_count":0,"area":"lr"},{"id":"2607.23700","title":"Offline-Online Curriculum RL for Multimodal Reasoning","created":"2026-07-26","cited_by_count":0,"area":"lr"},{"id":"2610.10889","title":"SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}