{"total":35,"rows":[{"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":"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":"2508.13998","title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","created":"2025-08-19","cited_by_count":38,"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":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"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":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"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":"2604.12627","title":"KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance","created":"2026-04-14","cited_by_count":8,"area":"lr"},{"id":"2510.23397","title":"VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations","created":"2025-10-27","cited_by_count":7,"area":"lr"},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2511.12908","title":"DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning","created":"2025-11-17","cited_by_count":5,"area":"lr"},{"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":"2601.00887","title":"VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition","created":"2025-12-31","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":"2604.01824","title":"STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering","created":"2026-04-02","cited_by_count":3,"area":"lr"},{"id":"2606.09248","title":"Temporal-Aware Reasoning Optimization for Video Temporal Grounding","created":"2026-06-08","cited_by_count":3,"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":"2512.19512","title":"Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation","created":"2025-12-22","cited_by_count":1,"area":"lr"},{"id":"2602.03102","title":"Consensus Group Relative Policy Optimization for Text Generation","created":"2026-02-03","cited_by_count":1,"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":"2603.18850","title":"HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models","created":"2026-03-19","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":"2606.26904","title":"Confidence-Aware Tool Orchestration for Robust Video Understanding","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2608.07417","title":"I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning","created":"2026-08-07","cited_by_count":1,"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":"2603.10300","title":"From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2606.11209","title":"ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"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":"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":"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":"2610.17656","title":"Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}