{"total":20,"rows":[{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2505.17540","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","created":"2025-05-23","cited_by_count":23,"area":"lr"},{"id":"2511.18437","title":"Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning","created":"2025-11-23","cited_by_count":20,"area":"lr"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"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":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"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":"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":"2602.23802","title":"EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"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":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2605.03485","title":"MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2512.14654","title":"ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2512.17213","title":"CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2606.17888","title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}