HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization

Documenti analoghi

• Better LLM Reasoning via Dual-Play
  di: Zhang, Zhengxin, et al.
  Pubblicazione: (2025)
• Policy-Gradient Training of Language Models for Ranking
  di: Gao, Ge, et al.
  Pubblicazione: (2023)
• Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
  di: Huang, Chengyu, et al.
  Pubblicazione: (2026)
• Self-Training Elicits Concise Reasoning in Large Language Models
  di: Munkhbat, Tergel, et al.
  Pubblicazione: (2025)
• Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
  di: Li, Yawei, et al.
  Pubblicazione: (2026)