跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1865新增论文
+1473其中 AI 相关
+176已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 17:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 17:49 — 2026-11-17 17:49(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 17:12库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,692 已收录论文21,414 AI 相关7,613 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v3arXiv:2607.11505

Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update for Large Language Models

Daocheng Fu, Rong Wu, Yu Yang, Jianbiao Mei, Licheng Wen, Xuemeng Yang, Yong Liu, Botian Shi 等 10 位作者

原文摘要

Reward-based reinforcement learning (RL) improves large language models but incurs substantial costs when repeated across targets. On-policy distillation (OPD) reuses experts by matching their distributions on target-generated trajectories, yet differing base policies can confound reward-induced updates with pre-existing policy differences, potentially distorting transferred update directions. We propose Proxy OPD (P-OPD), a post-training method that transfers reward-induced relative policy updates using the target's frozen base policy as a reference. A proxy undergoes reward-guided exploration, yielding token-level log-probability changes between its initial and optimized policies. These signals guide learning on target-generated trajectories, with calibration controlling signal absorption, enabling reuse of reward-induced improvements across targets. Experiments on Qwen3-family targets in mathematical reasoning, code generation, and instruction following show that P-OPD improves targets and outperforms conventional OPD in most settings. For 1.7B-to-8B transfer, average Math Mean@16 and Code Mean@8 scores exceed OPD by 8.3 and 3.4 points, respectively. Mechanism analyses show more faithful reward-induced supervision and controllable adaptation. Cross-scale and cross-generation experiments confirm signal transferability and reusability, while multi-domain distillation reveals synergistic gains and cross-domain interference. In the measured 4B-to-8B setting, target adaptation after proxy exploration takes approximately 15\% of direct target RL time; repeated signal reuse amortizes the one-time exploration cost across compatible models. These findings support relative policy updates as effective, transferable, and composable supervision for an ``explore once, transfer multiple times'' post-training paradigm.

cs.LG · cs.AI