arXiv · 2026 · Preprint · Author with a top-venue record

Denser ≠ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

M Wang, Hongyun Zhao, Wenzhuo Liu, L Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu

Date: 2026-07-02
Citations: 3
arXiv: 2607.01763 ↗

Cite

@misc{wang2026denser,
  title = {Denser ≠ Better: Limits of On-Policy Self-Distillation for Continual Post-Training},
  author = {M Wang and Hongyun Zhao and Wenzhuo Liu and L Yang and Geng Liu and Haiyang Guo and Guo-Sen Xie and Gaofeng Meng and Hongbin Liu and Fei Zhu},
  year = {2026},
  eprint = {2607.01763},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.01763},
}