Are Full Rollouts Necessary for On-Policy Distillation?

Documenti analoghi

• $π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
  di: Zhang, Yaocheng, et al.
  Pubblicazione: (2026)
• SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
  di: Fu, Yuqian, et al.
  Pubblicazione: (2025)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
  di: Fu, Yuqian, et al.
  Pubblicazione: (2025)
• AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
  di: Sun, Jingbo, et al.
  Pubblicazione: (2026)
• CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
  di: Zhang, Yaocheng, et al.
  Pubblicazione: (2025)