A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning

Documenti analoghi

• Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
  di: Peng, Ruiying, et al.
  Pubblicazione: (2026)
• A Recipe for Stable Offline Multi-agent Reinforcement Learning
  di: Lee, Dongsu, et al.
  Pubblicazione: (2026)
• Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
  di: Ahn, Hongjoon, et al.
  Pubblicazione: (2024)
• PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
  di: Wang, Ruheng, et al.
  Pubblicazione: (2025)
• Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
  di: Gan, Xingwei, et al.
  Pubblicazione: (2026)