Alibaba Qwen introduces QwenGyre elastic reinforcement learning framework
Original titleAlibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents
- Outlet
- MarkTechPost
- Published
- Importance
- 3/5
Summary
Alibaba's Qwen team released QwenGyre, an elastic reinforcement learning framework for extreme-long-horizon agent training. The system trains coding agents through unmodified, black-box harnesses on rollouts that run for hours and process close to 1 million tokens.
Original excerpt
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 […] The post Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents appeared first on MarkTechPost.