---
title: "Alibaba's QwenGyre trains coding agents on hour-long, million-token rollouts"
url: https://www.parallelquant.com/posts/alibaba-s-qwengyre-trains-coding-agents-on-hour-long-million-token-rollo-3ef252
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents/
published: 2026-10-12T21:41:50.000Z
topics: ["research", "llms"]
publisher: "Parallel Quant"
---

# Alibaba's QwenGyre trains coding agents on hour-long, million-token rollouts

*2026-10-12 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents/)*

Alibaba's Qwen team introduced QwenGyre, an elastic online reinforcement learning framework for extreme-long-horizon agents. It trains coding agents through unmodified, black-box harnesses, on rollouts that run for hours and consume close to 1M tokens.

**Why it matters:** Most agent RL has been limited to short episodes; training on hour-long trajectories directly targets the long-running autonomous work labs are now selling. Working with unmodified black-box harnesses means models can be trained against the same tooling used in production, narrowing the train/deploy gap.

**Topics:** research, llms

---
Read the original: https://www.marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents/
Canonical: https://www.parallelquant.com/posts/alibaba-s-qwengyre-trains-coding-agents-on-hour-long-million-token-rollo-3ef252
Published by Parallel Quant — https://www.parallelquant.com