Open-weight & owned stack · Training tuning
Alibaba Qwen Open-Sources QwenGyre Elastic Reinforcement Learning
Alibaba’s Qwen team open-sourced QwenGyre, an elastic reinforcement-learning framework for long-horizon agent training.
Read the original at marktechpost.comOpens the publisher's site in a new tabAlso covering this
@Alibaba_Qwen: QwenGyre elastic RLx.com, Oct 13Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents - MarkTechPostmarktechpost.com, Oct 12Qwen on X: "QwenGyre addresses two challenges of XLong-horizon agentic RL." / Xx.com, Oct 12Alibaba's Qwen team open sources QwenGyre to train AI agents that run for hours - Startup Fortunestartupfortune.com, Oct 13