Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper
•
2505.24726
•
Published
•
277
NLP
-
-
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 187 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 142 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Paper • 2505.04921 • Published • 186 -
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Paper • 2505.19147 • Published • 144 -
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 120