{"total":87,"rows":[{"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2509.24251","title":"Latent Visual Reasoning","created":"2025-09-29","cited_by_count":104,"area":"lr"},{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99,"area":"lr"},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97,"area":"lr"},{"id":"2506.21277","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","created":"2025-06-26","cited_by_count":55,"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":"2511.15661","title":"VisPlay: Self-Evolving Vision-Language Models from Images","created":"2025-11-19","cited_by_count":47,"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":"2508.21475","title":"MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents","created":"2025-08-29","cited_by_count":38,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2601.21821","title":"MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods","created":"2026-01-29","cited_by_count":30,"area":"lr"},{"id":"2509.25848","title":"More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models","created":"2025-09-30","cited_by_count":27,"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":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2601.01984","title":"Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation","created":"2026-01-05","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":"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":"2507.08306","title":"M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning","created":"2025-07-11","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":"2506.09079","title":"VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks","created":"2025-06-10","cited_by_count":14,"area":"mllm"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2507.02859","title":"Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation","created":"2025-07-03","cited_by_count":9,"area":"lr"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2512.09616","title":"Rethinking Chain-of-Thought Reasoning for Videos","created":"2025-12-10","cited_by_count":9,"area":"lr"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2512.03963","title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","created":"2025-12-03","cited_by_count":8,"area":"mllm"},{"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":"2602.04884","title":"Reinforced Attention Learning","created":"2026-02-04","cited_by_count":6,"area":"lr"},{"id":"2602.16742","title":"DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning","created":"2026-02-18","cited_by_count":6,"area":"lr"},{"id":"2510.09302","title":"CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2511.19417","title":"Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2511.20272","title":"VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"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":"2602.17555","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","created":"2026-02-19","cited_by_count":5,"area":"lr"},{"id":"2604.14568","title":"Learning Adaptive Reasoning Paths for Efficient Visual Reasoning","created":"2026-04-16","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":"2509.09658","title":"Measuring Epistemic Humility in Multimodal Large Language Models","created":"2025-09-11","cited_by_count":4,"area":"mllm"},{"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":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2512.24271","title":"Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation","created":"2025-12-30","cited_by_count":4,"area":"mllm"},{"id":"2602.03733","title":"RegionReasoner: Region-Grounded Multi-Round Visual Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2606.19120","title":"Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation","created":"2026-06-17","cited_by_count":4,"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":"2602.23823","title":"APPO: Attention-guided Perception Policy Optimization for Video Reasoning","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2605.13467","title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"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":"2512.18571","title":"ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning","created":"2025-12-21","cited_by_count":2,"area":"lr"},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.07274","title":"Structured Role-Aware Policy Optimization for Multimodal Reasoning","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2608.22429","title":"Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding","created":"2026-08-23","cited_by_count":2,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2509.10026","title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2511.19343","title":"Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning","created":"2025-11-24","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":"2601.22920","title":"Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.06024","title":"ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.13054","title":"Topo-R1: Detecting Topological Anomalies via Vision-Language Models","created":"2026-03-13","cited_by_count":1,"area":"mllm"},{"id":"2604.00479","title":"All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models","created":"2026-04-01","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":"2605.27154","title":"Touch-R1: Reinforcing Touch Reasoning in MLLMs","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.17678","title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.22158","title":"Improving Reasoning in Vision-Language Models via Perception Verified Self-Training","created":"2026-06-20","cited_by_count":1,"area":"lr"},{"id":"2607.01707","title":"LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2510.22282","title":"CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning","created":"2025-10-25","cited_by_count":0,"area":"lr"},{"id":"2511.18463","title":"Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2601.17197","title":"Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding","created":"2026-01-23","cited_by_count":0,"area":"lr"},{"id":"2605.09883","title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.23997","title":"IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2605.27311","title":"Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2605.29496","title":"On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2607.06522","title":"Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment","created":"2026-07-07","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":"2607.14547","title":"AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2607.17243","title":"LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning","created":"2026-07-19","cited_by_count":0,"area":"lr"},{"id":"2608.05631","title":"ChronoVision: Temporal Reasoning via Latent State Reconstruction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.26193","title":"AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.03729","title":"Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.35942","title":"Question-Specific Knowledge Graphs for Efficient Visual Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36798","title":"Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39168","title":"Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01908","title":"Same Reward, Different Skills: When Multimodal RL Learns to Look","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}