Scaling Reasoning Efficiently via Relaxed On-Policy Distillation

Documenti analoghi

• DistiLLM: Towards Streamlined Distillation for Large Language Models
  di: Ko, Jongwoo, et al.
  Pubblicazione: (2024)
• DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
  di: Ko, Jongwoo, et al.
  Pubblicazione: (2025)
• From Belief Entrenchment to Robust Reasoning in LLM Agents
  di: Oh, Jihwan, et al.
  Pubblicazione: (2025)
• Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
  di: Xu, Xin, et al.
  Pubblicazione: (2025)
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
  di: Zhao, Siyan, et al.
  Pubblicazione: (2026)