{"total":165,"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":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410,"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":"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":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2503.21620","title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","created":"2025-03-27","cited_by_count":168,"area":"lr"},{"id":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164,"area":"lr"},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124,"area":"lr"},{"id":"2509.07969","title":"Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search","created":"2025-09-09","cited_by_count":120,"area":"mllm"},{"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":"2505.19255","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","created":"2025-05-25","cited_by_count":90,"area":"lr"},{"id":"2505.11409","title":"Visual Planning: Let's Think Only with Images","created":"2025-05-16","cited_by_count":85,"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":"2505.15810","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","created":"2025-05-21","cited_by_count":74,"area":"lr"},{"id":"2503.11197","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering","created":"2025-03-14","cited_by_count":65,"area":"lr"},{"id":"2509.21100","title":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","created":"2025-09-25","cited_by_count":65,"area":"lr"},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62,"area":"lr"},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2507.03019","title":"Look-Back: Implicit Visual Re-focusing in MLLM Reasoning","created":"2025-07-02","cited_by_count":55,"area":"lr"},{"id":"2504.00883","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training","created":"2025-04-01","cited_by_count":51,"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":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2505.23762","title":"ZeroGUI: Automating Online GUI Learning at Zero Human Cost","created":"2025-05-29","cited_by_count":44,"area":"mllm"},{"id":"2506.01391","title":"AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning","created":"2025-06-02","cited_by_count":44,"area":"agents"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"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":"2509.01656","title":"Reinforced Visual Perception with Tools","created":"2025-09-01","cited_by_count":38,"area":"lr"},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"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":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2505.22453","title":"First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2505.21327","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","created":"2025-05-27","cited_by_count":33,"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":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2505.13031","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","created":"2025-05-19","cited_by_count":30,"area":"lr"},{"id":"2505.24871","title":"MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning","created":"2025-05-30","cited_by_count":30,"area":"mllm"},{"id":"2506.01725","title":"VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking","created":"2025-06-02","cited_by_count":30,"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":"2506.01908","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","created":"2025-06-02","cited_by_count":26,"area":"lr"},{"id":"2505.17163","title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning","created":"2025-05-22","cited_by_count":25,"area":"lr"},{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24,"area":null},{"id":"2508.12109","title":"Simple o3: Towards Interleaved Vision-Language Reasoning","created":"2025-08-16","cited_by_count":24,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"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":"2503.18071","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","created":"2025-03-23","cited_by_count":22,"area":"lr"},{"id":"2504.10358","title":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","created":"2025-04-14","cited_by_count":22,"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":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2509.21976","title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","created":"2025-09-26","cited_by_count":20,"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":"2505.10554","title":"Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models","created":"2025-05-15","cited_by_count":18,"area":"lr"},{"id":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18,"area":"lr"},{"id":"2601.18744","title":"TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models","created":"2026-01-26","cited_by_count":18,"area":"lr"},{"id":"2506.20332","title":"Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training","created":"2025-06-25","cited_by_count":17,"area":"lr"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2510.14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","created":"2025-10-16","cited_by_count":17,"area":"mllm"},{"id":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"id":"2506.08011","title":"Play to Generalize: Learning to Reason Through Game Play","created":"2025-06-09","cited_by_count":16,"area":"lr"},{"id":"2507.08306","title":"M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning","created":"2025-07-11","cited_by_count":16,"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":"2511.07403","title":"SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards","created":"2025-11-10","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","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":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"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":"2506.23840","title":"Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model","created":"2025-06-30","cited_by_count":14,"area":"lr"},{"id":"2503.14504","title":"Aligning Multimodal LLM with Human Preference: A Survey","created":"2025-03-18","cited_by_count":13,"area":"mllm"},{"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":"2510.00938","title":"Large Reasoning Models Learn Better Alignment from Flawed Thinking","created":"2025-10-01","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":"2507.07562","title":"The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs","created":"2025-07-10","cited_by_count":12,"area":"lr"},{"id":"2506.14907","title":"PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning","created":"2025-06-17","cited_by_count":11,"area":"lr"},{"id":"2509.25787","title":"Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking","created":"2025-09-30","cited_by_count":10,"area":"mllm"},{"id":"2510.06783","title":"TTRV: Test-Time Reinforcement Learning for Vision Language Models","created":"2025-10-08","cited_by_count":10,"area":"mllm"},{"id":"2602.11124","title":"PhyCritic: Multimodal Critic Models for Physical AI","created":"2026-02-11","cited_by_count":10,"area":"mllm"},{"id":"2505.20777","title":"TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs","created":"2025-05-27","cited_by_count":9,"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":"2506.21655","title":"APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization","created":"2025-06-26","cited_by_count":9,"area":"lr"},{"id":"2507.13362","title":"Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning","created":"2025-07-06","cited_by_count":9,"area":"lr"},{"id":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","cited_by_count":9,"area":"lr"},{"id":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2505.13973","title":"Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2505.24872","title":"ProxyThinker: Test-Time Guidance through Small Visual Reasoners","created":"2025-05-30","cited_by_count":8,"area":"lr"},{"id":"2506.17417","title":"Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?","created":"2025-06-20","cited_by_count":8,"area":"lr"},{"id":"2507.04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","created":"2025-07-06","cited_by_count":8,"area":null},{"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":"2507.16814","title":"Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning","created":"2025-07-22","cited_by_count":8,"area":"lr"},{"id":"2510.19307","title":"Unified Reinforcement and Imitation Learning for Vision-Language Models","created":"2025-10-22","cited_by_count":8,"area":"mllm"},{"id":"2601.09536","title":"Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning","created":"2026-01-14","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"}],"next_cursor":"100"}