# Alibaba's QwenGyre cuts agent reinforcement-learning wall-clock time by up to 1.85x by moving GPUs between rollout and training mid-run

On the 2.4-trillion-parameter Qwen 3.8, with rollouts of up to 700,000 tokens, Qwen reports a 6-point gain on NL2RepoBench, from 52.5% to 58.5%, in 48 training steps.

- Published: 2026-10-13T06:13:53.502Z
- Canonical: https://polylog.news/ai/2026-10-13/alibaba-s-qwengyre-cuts-agent-reinforcement-learning-wall-cl
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2609.33848), [Startup Fortune](https://startupfortune.com/alibabas-qwen-team-open-sources-qwengyre-to-train-ai-agents-that-run-for-hours/), [FourWeekMBA](https://fourweekmba.com/ai-alibaba-unveils-qwengyre-to-speed-up-training-of-ai-agents/)

Alibaba's Qwen team released QwenGyre, a reinforcement-learning framework for training agents on tasks that run for hours and generate hundreds of thousands of tokens. AI ML Big Data described the problem it targets. In agent reinforcement…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-13/alibaba-s-qwengyre-cuts-agent-reinforcement-learning-wall-cl (subscription information: https://polylog.news/pricing).