**ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillati

**ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation**

> On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally regardless of their informativeness. We observe a consistent asymmetry in controlled filtering experiments: in both OPD and on-policy self distillation (OPSD), training only on incorrect SGOs outperforms training only on correct ones. Our fu...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：行业
- **发布时间**：2026-06-25 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2606.23104)