{"slug": "alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong", "title": "Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents", "summary": "Alibaba's Qwen team introduced QwenGyre, an online elastic reinforcement learning framework that trains coding agents through unmodified, black-box harnesses. QwenGyre targets extreme-long-horizon rollouts that run for hours and process close to 1M tokens, and was used on Qwen's own models.", "body_md": "Alibaba’s Qwen team has introduced QwenGyre, an elastic reinforcement learning RL framework for extreme-long-horizon agent training. QwenGyre is an online reinforcement learning system from Alibaba that trains coding agents through unmodified, black-box harnesses. It targets rollouts that run for hours and process close to 1M tokens. The QwenGyre elastic RL framework was used on Qwen’s […]\n\nThe post [Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents](https://www.marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong", "canonical_source": "https://www.marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents/", "published_at": "2026-10-12 21:41:50+00:00", "updated_at": "2026-10-12 22:22:59.318996+00:00", "lang": "en", "topics": ["ai-agents", "machine-learning", "artificial-intelligence", "ai-research", "large-language-models"], "entities": ["Alibaba", "Qwen", "QwenGyre"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong", "markdown": "https://wpnews.pro/news/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong.md", "text": "https://wpnews.pro/news/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong.txt", "jsonld": "https://wpnews.pro/news/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong.jsonld"}}