← Back to all news
arXiv Machine Learning By Yukun Tian, Junwei Su, Haofeng Xu, Lansong Diao, Zhengping Qian, Weibo Zhao, Wenchao Zhou, Ruiting Zhou, Chuan Wu

ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training

Read the original on arXiv Machine Learning →

ReFlow is a system‑algorithm co‑designed framework for efficient reinforcement learning (RL) post‑training of large language models (LLMs). It introduces replay‑driven decoupling, allowing recent trajectories to be reused multiple times to amortize rollout costs while limiting policy staleness. The architecture features a dual replay cycle, an elastic resource pool, and an adaptive scheduler, achieving up to 2.06× higher training throughput compared to existing synchronous and asynchronous RL systems without sacrificing model performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 20

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

The paper introduces Reverse‑Turn Policy Optimization (RTPO), a method that restructures multi‑turn agentic reinforcement learning rollouts into sparse reverse trees and updates policies in temporal reverse order. This approach addresses three key instability sources—context mismatch, weak turn‑level credit assignment, and asynchronous policy drift—by aligning each decision with its downstream continuation. Theoretical analysis shows RTPO eliminates context mismatch and drift, reduces credit bias, and converges to recursive optimality, while experiments demonstrate performance gains of 21.50% over trajectory‑level and 10.76% over turn‑level baselines on multi‑turn agentic RL benchmarks.

By Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu
llmsagentsreinforcement-learningbenchmarkssafety
More like this →
arXiv Machine Learning
Jul 21

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training

arXiv:2604. 26256v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline.

By Tianhao Hu, Xiangcheng Liu, Yuchun Miao, Youshao Xiao, Hongyu Zang, Yang Zheng, Xuan Huang, Jinrui Ding, Yufei Zhang, Yu Yang, Yi-Kai Zhang, Yueqing Sun, Chengcheng Han, Xiandi Ma, Wei Wang, Qi Gu, Yerui Sun, Yuchen Xie, Xunliang Cai
llmsagentsreinforcement-learningefficiencybenchmarks
More like this →