Alibaba Details QwenGyre to Accelerate Extreme-Horizon Agent Training

Alibaba's Qwen team, with USTC and Tsinghua, released QwenGyre, an elastic RL framework for extreme-long-horizon agent training. An Elastic Scheduler shifts GPUs between rollout generation and training to cut idling and trajectory redundancy; single rollouts often consume 700,000 to about 1 million tokens.

• Alibaba launches Qwen Audio 3.1, cuts prices2026-09-23
• Balance of Power in Open Models: Chinese Firms Lead Open-Weight2026-09-23
• US government site removes Alibaba Qwen model2026-09-18
• Alibaba Unveils $450 AI Glasses2026-10-13
• China's AI Expansion in Latin America Raises Security Concerns2026-10-13