{"total":93,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91,"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":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49,"area":"lr"},{"id":"2510.26802","title":"Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark","created":"2025-10-30","cited_by_count":43,"area":"lr"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29,"area":"agents"},{"id":"2509.23652","title":"ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis","created":"2025-09-28","cited_by_count":26,"area":"lr"},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2601.23224","title":"Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning","created":"2026-01-30","cited_by_count":24,"area":"lr"},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22,"area":"lr"},{"id":"2603.12262","title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","created":"2026-03-12","cited_by_count":22,"area":"lr"},{"id":"2512.16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","created":"2025-12-18","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":"2510.09606","title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","created":"2025-10-10","cited_by_count":19,"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":"2505.20715","title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","created":"2025-05-27","cited_by_count":12,"area":"mllm"},{"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":"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":"2605.06094","title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","created":"2026-05-07","cited_by_count":10,"area":"lr"},{"id":"2511.23477","title":"Video-CoM: Interactive Video Reasoning via Chain of Manipulations","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2602.01334","title":"What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom","created":"2026-02-01","cited_by_count":9,"area":"mllm"},{"id":"2603.26586","title":"MA-Bench: Towards Fine-grained Micro-Action Understanding","created":"2026-03-27","cited_by_count":9,"area":"mllm"},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"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":"2602.07801","title":"VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos","created":"2026-02-08","cited_by_count":7,"area":"agents"},{"id":"2604.01569","title":"VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2511.13054","title":"ViSS-R1: Self-Supervised Reinforcement Video Reasoning","created":"2025-11-17","cited_by_count":6,"area":"lr"},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2605.20342","title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","created":"2026-05-19","cited_by_count":6,"area":"mllm"},{"id":"2511.20272","title":"VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2512.16978","title":"A Benchmark for Omni-Modal Reasoning in Long Videos","created":"2025-12-18","cited_by_count":5,"area":"lr"},{"id":"2603.14659","title":"VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting","created":"2026-03-15","cited_by_count":4,"area":"distill"},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2603.18856","title":"Motion-o: Trajectory-Grounded Video Reasoning","created":"2026-03-19","cited_by_count":4,"area":"lr"},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","created":"2026-06-17","cited_by_count":4,"area":null},{"id":"2509.15602","title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","created":"2025-09-19","cited_by_count":3,"area":"mllm"},{"id":"2602.23823","title":"APPO: Attention-guided Perception Policy Optimization for Video Reasoning","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2603.16256","title":"When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2604.16243","title":"Find, Fix, Reason: Context Repair for Video Reasoning","created":"2026-04-17","cited_by_count":3,"area":"mllm"},{"id":"2604.26707","title":"CurEvo: Curriculum-Guided Self-Evolution for Video Understanding","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.07299","title":"EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams","created":"2026-05-08","cited_by_count":3,"area":"mllm"},{"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":"2508.10955","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2602.13332","title":"MedScope: Incentivizing \"Think with Videos\" for Clinical Reasoning via Coarse-to-Fine Tool Calling","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2604.04379","title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2605.01324","title":"Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs","created":"2026-05-02","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":"2606.05259","title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.24636","title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2607.03069","title":"SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection","created":"2026-07-03","cited_by_count":2,"area":"lr"},{"id":"2602.05829","title":"Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2603.06561","title":"EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.21988","title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.26680","title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.18441","title":"Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.30026","title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.05090","title":"Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.02078","title":"CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding","created":"2026-08-03","cited_by_count":1,"area":"mllm"},{"id":"2608.13226","title":"CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2609.02231","title":"PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.04203","title":"Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision","created":"2026-09-03","cited_by_count":1,"area":"distill"},{"id":"2609.06475","title":"Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding","created":"2026-09-06","cited_by_count":1,"area":"lr"},{"id":"2507.19821","title":"LAVA: Language Driven Scalable and Versatile Traffic Video Analytics","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2511.18463","title":"Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2512.01424","title":"ViRectify: A Challenging Benchmark for Video Reasoning Correction with Multimodal Large Language Models","created":"2025-12-01","cited_by_count":0,"area":"lr"},{"id":"2601.07298","title":"Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2604.00696","title":"TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2604.19218","title":"Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.01657","title":"Act2See: Emergent Active Visual Perception for Video Reasoning","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2605.04733","title":"Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.06121","title":"Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.08974","title":"Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.25461","title":"MetaphorVU: Towards Metaphorical Video Understanding","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.19927","title":"CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.22870","title":"VideoLatent: Video-Language Learning via Latent Self-Forcing","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.00867","title":"EFlow: Learning Evidence Flow for Long-Video Reasoning with Adaptive Reflection","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.05089","title":"TimeThink: Reasoning with Time for Video LLMs","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2608.04124","title":"Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.20814","title":"Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2608.26495","title":"Video-FLAIR: Not Whether to Reason, But How","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.15606","title":"VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding","created":"2026-09-14","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":"2609.29607","title":"STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2609.36782","title":"Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.03400","title":"Beyond Entropy: Self-Diagnostic Multi-Role Token Optimization for Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.04911","title":"VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.17656","title":"Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}