{"total":64,"rows":[{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"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":"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":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"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":"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":"2511.04460","title":"V-Thinker: Interactive Thinking with Images","created":"2025-11-06","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":"2506.07905","title":"WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning","created":"2025-06-09","cited_by_count":21,"area":"lr"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"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":"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":"2505.22651","title":"Sherlock: Self-Correcting Reasoning in Vision-Language Models","created":"2025-05-28","cited_by_count":13,"area":"lr"},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","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":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2510.14738","title":"AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning","created":"2025-10-16","cited_by_count":11,"area":"lr"},{"id":"2602.07605","title":"Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning","created":"2026-02-07","cited_by_count":11,"area":"lr"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2506.04559","title":"Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2506.22434","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning","created":"2025-06-27","cited_by_count":9,"area":"lr"},{"id":"2510.01681","title":"Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning","created":"2025-10-02","cited_by_count":9,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2603.28618","title":"Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning","created":"2026-03-30","cited_by_count":9,"area":"lr"},{"id":"2511.22586","title":"Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization","created":"2025-11-27","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":"2604.01840","title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","created":"2026-04-02","cited_by_count":7,"area":"lr"},{"id":"2511.13190","title":"Video Spatial Reasoning with Object-Centric 3D Rollout","created":"2025-11-17","cited_by_count":6,"area":"lr"},{"id":"2601.06801","title":"Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy","created":"2026-01-11","cited_by_count":6,"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":"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":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","cited_by_count":5,"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":"2509.24776","title":"VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2602.08503","title":"Learning Self-Correction in Vision-Language Models via Rollout Augmentation","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2602.21743","title":"Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization","created":"2026-02-25","cited_by_count":4,"area":"lr"},{"id":"2510.08964","title":"Unleashing Perception-Time Scaling to Multimodal Reasoning Models","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2603.01106","title":"DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage","created":"2026-03-01","cited_by_count":3,"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":"2605.09262","title":"Reinforcing Multimodal Reasoning Against Visual Degradation","created":"2026-05-10","cited_by_count":2,"area":"lr"},{"id":"2603.14811","title":"Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning","created":"2026-03-16","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":"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":"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":"2605.22072","title":"Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2606.03937","title":"Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2511.06722","title":"Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View","created":"2025-11-10","cited_by_count":0,"area":"lr"},{"id":"2511.13242","title":"MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection","created":"2025-11-17","cited_by_count":0,"area":"lr"},{"id":"2512.10414","title":"Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2603.22689","title":"Think 360{\\deg}: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2606.23543","title":"VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2606.29812","title":"Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2607.12786","title":"CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.13931","title":"SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.19156","title":"Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes","created":"2026-07-24","cited_by_count":0,"area":"lr"},{"id":"2609.25773","title":"Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.36572","title":"Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}