2 papers
cs.CL2025
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Zengzhi Wang, Fan Zhou, Xuefeng Li +1
Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive…
cs.CL2024
Progress or Regress? Self-Improvement Reversal in Post-training
Ting Wu, Xuefeng Li, Pengfei Liu
Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning…