Cites: On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

10 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
  arxiv:2402.03300 · evidence: id
• The Llama 3 Herd of Models
  arxiv:2407.21783 · evidence: id
• LIMO: Less is More for Reasoning
  arxiv:2502.03387 · evidence: id
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
  arxiv:2503.14476 · evidence: id
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  arxiv:2504.13837 · evidence: id
• Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
  arxiv:2506.01939 · evidence: id
• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
  arxiv:2506.13585 · evidence: id
• Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
  arxiv:2507.12856 · evidence: id
• On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
  arxiv:2508.05629 · evidence: id
• Reinforcement Learning from Human Feedback
  url:rlhfbook.com · evidence: title