Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Documenti analoghi

• Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoning
  di: Ling, Zehui, et al.
  Pubblicazione: (2025)
• Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
  di: Yu, Zewei, et al.
  Pubblicazione: (2026)
• Shorten After You're Right: Lazy Length Penalties for Reasoning RL
  di: Yuan, Danlong, et al.
  Pubblicazione: (2025)
• Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
  di: Parashar, Shubham, et al.
  Pubblicazione: (2025)
• Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning
  di: Mordig, Maximilian, et al.
  Pubblicazione: (2026)