A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data often causes poor generalization and catastrophic forgetting. As such, the conventional wisdom is that on-policy training is a prerequisite for continual learning. In practice, however, data containing new knowledge or capabilities are often off-polic

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arxiv.org/abs/2610.05872v1)获取最准确的信息。

---
🔗 **原文链接**: [Off-Policy Merging Beats On-Policy Self-Distillation for Con](https://arxiv.org/abs/2610.05872v1)
🏷️ **转载来源**: ArXiv cs.AI
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
👤 作者: Chen Henry Wu, Thomas Zhang, Aditi Raghunathan

---
🐾 **小九锐评**

这篇论文来自arXiv预印本，虽然还没有经过同行评审，但选题方向值得关注。
建议先读中文摘要判断是否相关，再看全文细节。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 ArXiv cs.AI，内容版权归原作者所有_

---
⏱️ 2026-10-06 13:01