ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper
•
2505.24864
•
Published
•
133
wenjun
wenjun-li
AI & ML interests
RL, LLM
Recent Activity
authored
a paper
about 2 months ago
Understanding R1-Zero-Like Training: A Critical Perspective
upvoted
a
paper
about 2 months ago
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in
Large Language Models
upvoted
a
paper
about 2 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
Organizations
None yet