ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper
•
2505.24864
•
Published
•
143
Oliver Stanley
OllieStanley
AI & ML interests
Language models, AI alignment, computer vision
Organizations
upvoted
4
papers
7 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper
•
2506.01939
•
Published
•
187
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Paper
•
2506.00577
•
Published
•
11
REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Paper
•
2505.24760
•
Published
•
74