Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA Paper • 2505.21115 • Published May 27, 2025 • 140
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 187
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models Paper • 2505.24864 • Published May 30, 2025 • 143
