{"total":84,"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":"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":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56,"area":"lr"},{"id":"2512.14698","title":"TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs","created":"2025-12-16","cited_by_count":50,"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":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42,"area":"lr"},{"id":"2509.24786","title":"LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning","created":"2025-09-29","cited_by_count":27,"area":"lr"},{"id":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27,"area":null},{"id":"2512.22315","title":"VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning","created":"2025-12-26","cited_by_count":27,"area":"lr"},{"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":"2512.15693","title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","created":"2025-12-17","cited_by_count":25,"area":"lr"},{"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":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2512.06810","title":"MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning","created":"2025-12-07","cited_by_count":22,"area":"mllm"},{"id":"2603.12262","title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","created":"2026-03-12","cited_by_count":22,"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":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2512.04540","title":"VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management","created":"2025-12-04","cited_by_count":19,"area":"mllm"},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2511.13026","title":"REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding","created":"2025-11-17","cited_by_count":16,"area":"lr"},{"id":"2602.20739","title":"PyVision-RL: Forging Open Agentic Vision Models via RL","created":"2026-02-24","cited_by_count":16,"area":"agents"},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16,"area":null},{"id":"2510.17777","title":"SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference","created":"2025-10-20","cited_by_count":15,"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":"2605.06094","title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","created":"2026-05-07","cited_by_count":10,"area":"lr"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2603.12254","title":"Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"id":"2603.17307","title":"Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding","created":"2026-03-18","cited_by_count":9,"area":"agents"},{"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":"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":"2602.11499","title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2603.11896","title":"Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models","created":"2026-03-12","cited_by_count":8,"area":"lr"},{"id":"2603.26639","title":"Make Geometry Matter for Spatial Reasoning","created":"2026-03-27","cited_by_count":8,"area":"lr"},{"id":"2603.28610","title":"ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2602.04094","title":"VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding","created":"2026-02-04","cited_by_count":7,"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":"2511.19524","title":"VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning","created":"2025-11-24","cited_by_count":6,"area":"mllm"},{"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":"2510.15440","title":"Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning","created":"2025-10-17","cited_by_count":5,"area":"lr"},{"id":"2511.19972","title":"Boosting Reasoning in Large Multimodal Models via Activation Replay","created":"2025-11-25","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":"2604.05117","title":"Watch Before You Answer: Learning from Visually Grounded Post-Training","created":"2026-04-06","cited_by_count":5,"area":"mllm"},{"id":"2602.18702","title":"Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding","created":"2026-02-21","cited_by_count":4,"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":"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":"2607.13681","title":"Towards Spatial Supersensing in the Wild","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2601.06176","title":"TIR-Flow: Active Video Search and Reasoning with Frozen VLMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2602.11730","title":"STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2603.29616","title":"Video-Oasis: Rethinking Evaluation of Video Understanding","created":"2026-03-31","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":"2606.05172","title":"Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing","created":"2026-04-16","cited_by_count":3,"area":"diffusion"},{"id":"2606.24286","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2512.00805","title":"Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding","created":"2025-11-30","cited_by_count":2,"area":"lr"},{"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":"2603.22285","title":"VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2605.21917","title":"MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2606.05259","title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","created":"2026-06-03","cited_by_count":2,"area":null},{"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":"2605.09422","title":"Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2605.15764","title":"GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2606.03301","title":"SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.15320","title":"Conditional Multi-Event Temporal Grounding in Long-Form Video","created":"2026-06-13","cited_by_count":1,"area":"mllm"},{"id":"2609.09300","title":"Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding","created":"2026-09-08","cited_by_count":1,"area":"distill"},{"id":"2512.17229","title":"Video Detective: Seek Critical Clues Recurrently to Answer Question from Long Videos","created":"2025-12-19","cited_by_count":0,"area":"mllm"},{"id":"2603.19481","title":"Narrative Aligned Long Form Video Question Answering","created":"2026-03-19","cited_by_count":0,"area":"mllm"},{"id":"2604.16405","title":"ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models","created":"2026-03-31","cited_by_count":0,"area":"wm"},{"id":"2606.24369","title":"Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.01086","title":"LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.24582","title":"CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding","created":"2026-07-27","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":"2608.06756","title":"Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence","created":"2026-08-07","cited_by_count":0,"area":"mllm"},{"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":"2609.38413","title":"VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.39021","title":"Frame Differential On-Policy Self-Distillation for Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.10893","title":"Less from More: Reinforcing Sparse Video Reasoning from Dense References","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.18844","title":"RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}