The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL

Documenti analoghi

• Trust Region Masking for Long-Horizon LLM Reinforcement Learning
  di: Li, Yingru, et al.
  Pubblicazione: (2025)
• Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail
  di: Li, Yingru, et al.
  Pubblicazione: (2025)
• Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It
  di: Zhang, Yaxiang, et al.
  Pubblicazione: (2026)
• A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms
  di: Li, Yingru, et al.
  Pubblicazione: (2025)
• SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  di: Xue, Zhenghai, et al.
  Pubblicazione: (2025)