{"total":15,"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":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"area":"lr"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2511.19773","title":"Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs","created":"2025-11-24","cited_by_count":17,"area":"lr"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2602.12395","title":"What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2508.11196","title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","created":"2025-08-15","cited_by_count":3,"area":"lr"},{"id":"2602.01034","title":"Discovering Process-Outcome Credit in Multi-Step LLM Reasoning","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2512.12487","title":"More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models","created":"2025-12-13","cited_by_count":1,"area":"lr"},{"id":"2510.21807","title":"Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2512.18956","title":"Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2606.30217","title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2608.13766","title":"ChartProbe: A Diagnostic Study on Visual Reasoning through Perception, Grounding, and Simple Reasoning","created":"2026-08-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}