{"total":22,"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":"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":"2510.23473","title":"Video-Thinker: Sparking \"Thinking with Videos\" via Reinforcement Learning","created":"2025-10-27","cited_by_count":34,"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":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2508.03100","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":"2601.19686","title":"Video-KTR: Reinforcing Video Reasoning via Key Token Attribution","created":"2026-01-27","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":"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":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","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":"2506.22880","title":"Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder","created":"2025-06-28","cited_by_count":2,"area":"lr"},{"id":"2603.25942","title":"Reinforcing Structured Chain-of-Thought for Video Understanding","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"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":"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":"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":"2602.00504","title":"RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding","created":"2026-01-31","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":"2609.39021","title":"Frame Differential On-Policy Self-Distillation for Video Reasoning","created":"2026-09-30","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}