Cited by: DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

67 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.

• iGRPO: Self-Feedback-Driven LLM Reasoning
  arxiv:2602.09000 · evidence: id
• Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
  arxiv:2602.18037 · evidence: id
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
  arxiv:2604.02288 · evidence: id
• Skip-Connected Policy Optimization for Implicit Advantage
  arxiv:2604.08690 · evidence: id
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
  arxiv:2604.13016 · evidence: id
• Structured Scaling of AI Discovery Across Diverse Scientific Domains
  arxiv:2604.19341 · evidence: id
• GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
  arxiv:2604.20659 · evidence: id
• Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
  arxiv:2605.06241 · evidence: id
• Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
  arxiv:2605.12969 · evidence: id
• From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
  arxiv:2605.22074 · evidence: id
• Weight-Space Geometry of Offline Reasoning Training
  arxiv:2606.23740 · evidence: id
• When Does Continual Learning Require Learning
  arxiv:2607.07847 · evidence: id
• Latent On-Policy Self-Distillation
  arxiv:2608.13040 · evidence: id
• SPADE: Self-Play in Adaptive Synthetic Executable Environments
  arxiv:2608.19197 · evidence: id
• TTPO: Test-Time Policy Optimization
  arxiv:2608.27448 · evidence: id
• Recursive Self-Improvement via On-Policy Distillation for Reasoning
  arxiv:2609.30652 · evidence: title
• RLTL;DR: Self-improvement by Internalizing Self-generated Feedback
  arxiv:2609.37633 · evidence: id
• GRPO++: Tricks for Making RL Actually Work (Cameron Wolfe)
  url:cameronrwolfe.substack.com/p/grpo-tricks · evidence: id
• LoRA Without Regret (Thinking Machines)
  url:thinkingmachines.ai/blog/lora · evidence: id