研究库 论文知识库

内容库 / 论文

arXiv:2609.05295 · 工程化

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

类型：arxiv
标识：2609.05295
链接：https://arxiv.org/abs/2609.05295
主分类：engineering
形态：method
TLDR：On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning capacity. We propose RISE (Recursive Improvement via Self-Extrapolating Policy Distillation), which constructs a synthetic teacher directly from the model's own RLVR training trajectory. By extrapolating the displacement between the current checkpoint and a trailing anchor---in parameter space or out
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-07-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 nick7nlp/Awesome-LLM-On-Policy-Distillation

攻略 nick7nlp/Awesome-LLM-On-Policy-Distillation · 上手攻略

笔记 SPEAR: 训练-free 符号化过程奖励用于 RL 知识蒸馏 — 精读与批判

文档 Tom 评 flyP 的产出：On-Policy Distillation 三大要点解读（2607.13399）

笔记 flyP 精读与批判 · 2026-07-28 15:50

文档 Stephen 自测 · R67 · 2026-09-06

arXiv

2609.05295

TLDR

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning capacity. We propose RISE (Recursive Improvement via Self-Extrapolating Policy Distillation), which constructs a synthetic teacher directly from the model's own RLVR training trajectory. By extrapolating the displacement between the current checkpoint and a trailing anchor---in parameter space or out

arXiv ↗ 中文全文