Alibaba’s QwenGyre Tackles The Million-Token Problem With Elastic GPU Scheduling For XLong RL

To improve your local-language experience, sometimes we employ an auto-translation plugin. Please note auto-translation may not be accurate, so read original article for precise information. Alibaba’s QwenGyre brings elastic GPU scheduling and trajectory deduplication to extreme-long-horizon RL, boosting NL2RepoBench scores by 6% and cutting training time up to 44%. Alibaba has introduced QwenGyre, a reinforcement learning framework designed for what the research team calls “XLong-horizon” agent training — tasks in which a single rollout can run for hours, involve hundreds of model–environment interactions, and consume close to one million tokens.