Cites: Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

4 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.

• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
  arxiv:2503.14476 · evidence: title
• Olmo 3
  arxiv:2512.13961 · evidence: id
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
  arxiv:2601.18734 · evidence: title
• Reinforcement Learning via Self-Distillation
  arxiv:2601.20802 · evidence: title