{"total":124,"rows":[{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61,"area":"lr"},{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"area":"lr"},{"id":"2507.03019","title":"Look-Back: Implicit Visual Re-focusing in MLLM Reasoning","created":"2025-07-02","cited_by_count":55,"area":"lr"},{"id":"2505.16673","title":"R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO","created":"2025-05-22","cited_by_count":52,"area":"lr"},{"id":"2505.17022","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","created":"2025-05-22","cited_by_count":52,"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":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2509.21268","title":"MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources","created":"2025-09-25","cited_by_count":39,"area":"lr"},{"id":"2509.25541","title":"Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play","created":"2025-09-29","cited_by_count":37,"area":"mllm"},{"id":"2511.16334","title":"OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe","created":"2025-11-20","cited_by_count":37,"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":"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":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"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":"2508.10433","title":"We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning","created":"2025-08-14","cited_by_count":32,"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":"2505.24875","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2506.04034","title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","created":"2025-06-04","cited_by_count":26,"area":"lr"},{"id":"2507.22607","title":"VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning","created":"2025-07-30","cited_by_count":26,"area":"lr"},{"id":"2505.18842","title":"v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning","created":"2025-05-24","cited_by_count":25,"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":"2511.18437","title":"Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning","created":"2025-11-23","cited_by_count":20,"area":"lr"},{"id":"2505.11462","title":"Disentangling Reasoning and Knowledge in Medical Large Language Models","created":"2025-05-16","cited_by_count":18,"area":"lr"},{"id":"2505.19094","title":"SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring","created":"2025-05-25","cited_by_count":17,"area":"lr"},{"id":"2509.13031","title":"Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models","created":"2025-09-16","cited_by_count":17,"area":"lr"},{"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":"2509.12132","title":"Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models","created":"2025-09-15","cited_by_count":16,"area":"lr"},{"id":"2602.22190","title":"GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL","created":"2026-02-25","cited_by_count":16,"area":"agents"},{"id":"2506.22146","title":"Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs","created":"2025-06-27","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":"2506.09736","title":"Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation","created":"2025-06-11","cited_by_count":14,"area":"lr"},{"id":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"area":"lr"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2605.15864","title":"Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination","created":"2026-05-15","cited_by_count":13,"area":"mllm"},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"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":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2509.22624","title":"SPARK: Synergistic Policy And Reward Co-Evolving Framework","created":"2025-09-26","cited_by_count":10,"area":"mllm"},{"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":"2601.10094","title":"V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2601.19686","title":"Video-KTR: Reinforcing Video Reasoning via Key Token Attribution","created":"2026-01-27","cited_by_count":10,"area":"lr"},{"id":"2509.21854","title":"Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2603.02024","title":"MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning","created":"2026-03-02","cited_by_count":9,"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":"2507.16518","title":"SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical 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":"2512.18215","title":"Stable and Efficient Single-Rollout RL for Multimodal Reasoning","created":"2025-12-20","cited_by_count":8,"area":"lr"},{"id":"2603.03825","title":"From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning","created":"2026-03-04","cited_by_count":8,"area":"lr"},{"id":"2506.14821","title":"Reinforcing VLMs to Use Tools for Detailed Visual Reasoning Under Resource Constraints","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2510.01719","title":"What MLLMs Learn about When they Learn about Multimodal Reasoning","created":"2025-10-02","cited_by_count":6,"area":"lr"},{"id":"2511.13054","title":"ViSS-R1: Self-Supervised Reinforcement Video Reasoning","created":"2025-11-17","cited_by_count":6,"area":"lr"},{"id":"2512.12218","title":"Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking","created":"2025-12-13","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":"2605.20177","title":"From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2510.21122","title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2512.12690","title":"Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2512.17227","title":"Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning","created":"2025-12-19","cited_by_count":5,"area":"lr"},{"id":"2602.09439","title":"Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning","created":"2026-02-10","cited_by_count":5,"area":null},{"id":"2602.21628","title":"RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2604.21409","title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","created":"2026-04-23","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":"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":"2603.13842","title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","created":"2026-03-14","cited_by_count":4,"area":"driving"},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2604.24583","title":"Improving Vision-language Models with Perception-centric Process Reward Models","created":"2026-04-27","cited_by_count":4,"area":"lr"},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2606.11576","title":"AVIS: Adaptive Test-Time Scaling for Vision-Language Models","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2606.22565","title":"Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do","created":"2026-06-21","cited_by_count":4,"area":"lr"},{"id":"2508.06009","title":"MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models","created":"2025-08-08","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":"2510.15050","title":"DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2511.16670","title":"Learning to Think Fast and Slow for Visual Language Models","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2602.13235","title":"Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2605.16079","title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","created":"2026-05-15","cited_by_count":3,"area":"mllm"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2509.23322","title":"Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework","created":"2025-09-27","cited_by_count":2,"area":"lr"},{"id":"2509.26594","title":"Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces","created":"2025-09-30","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":"2603.02099","title":"Recursive Think-Answer Process for LLMs and VLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.18118","title":"Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.10219","title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","created":"2026-04-11","cited_by_count":2,"area":"lr"},{"id":"2605.09262","title":"Reinforcing Multimodal Reasoning Against Visual Degradation","created":"2026-05-10","cited_by_count":2,"area":"lr"},{"id":"2605.24794","title":"DUEL: Adversarial Self-Play for Multimodal Reasoning","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2606.06076","title":"Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation","created":"2026-06-04","cited_by_count":2,"area":"mllm"},{"id":"2606.16122","title":"Thinking with Visual Grounding","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2512.12487","title":"More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models","created":"2025-12-13","cited_by_count":1,"area":"lr"},{"id":"2512.16698","title":"Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning","created":"2025-12-18","cited_by_count":1,"area":"lr"},{"id":"2601.00501","title":"CPPO: Contrastive Perception Policy Optimization for VLM Agents","created":"2026-01-01","cited_by_count":1,"area":"agents"},{"id":"2603.00207","title":"VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models","created":"2026-02-27","cited_by_count":1,"area":"lr"},{"id":"2603.26126","title":"Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2605.01882","title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","created":"2026-05-03","cited_by_count":1,"area":"lr"},{"id":"2605.16460","title":"REC-RL: Referring expression counting via Gaussian and range-based reward optimization","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.25571","title":"AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution","created":"2026-05-25","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}