recurring author
Yuhao Shen
2 archived notes
Related Notes
按论文归档时间排序，展示该作者在本站已经出现的材料。
归档 更新
SEED: Self Evolving On Policy Distillation for Agentic Reinforcement Learning
先用外部模型标注的轨迹—技能数据把策略训练成轨迹分析器，再让每轮最新策略从自身完整轨迹生成事后技能并对同批采样 token 做门控似然训练；三种小模型在 12 个汇总指标中取得 10 个最优或并列最优，但直接前作 OPID 未进入主表，且证据缺少多随机种子、技能正确性评测与总训练成本对齐。
待审阅 2607.14777-seed-self-evolving-on-policy-distillation On-Policy DistillationAgent RLCredit Assignment
归档 更新
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
以 TV loss 训练 MTP heads，并用 probabilistic rejection sampling 提高 RL rollout 接受率。
待审阅 2606.12370-bebop-mtp-rejection-sampling-rl-training Rollout OptimizationSpeculative DecodingMulti-Token Prediction