{"total":15,"rows":[{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24,"area":null},{"id":"2509.21976","title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","created":"2025-09-26","cited_by_count":20,"area":null},{"id":"2507.04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2602.15772","title":"Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2606.06294","title":"Towards One-to-Many Temporal Grounding","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2505.19611","title":"Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2511.23151","title":"Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2603.06958","title":"Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2606.09092","title":"From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2508.07804","title":"Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning","created":"2025-08-11","cited_by_count":0,"area":null},{"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":"2605.10445","title":"Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":null}