{"total":21,"rows":[{"id":"2509.24251","title":"Latent Visual Reasoning","created":"2025-09-29","cited_by_count":104,"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":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"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":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"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":"2604.01840","title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","created":"2026-04-02","cited_by_count":7,"area":"lr"},{"id":"2601.06801","title":"Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"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":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2512.08980","title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","created":"2025-12-05","cited_by_count":4,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"area":"lr"},{"id":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","cited_by_count":2,"area":"lr"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2601.07238","title":"Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2607.19790","title":"Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning","created":"2026-07-22","cited_by_count":1,"area":"lr"}],"next_cursor":null}