Alibaba's QwenGyre trains coding agents on hour-long, million-token rollouts

Alibaba's Qwen team introduced QwenGyre, an elastic online reinforcement learning framework for extreme-long-horizon agents. It trains coding agents through unmodified, black-box harnesses, on rollouts that run for hours and consume close to 1M tokens.

Why it matters: Most agent RL has been limited to short episodes; training on hour-long trajectories directly targets the long-running autonomous work labs are now selling. Working with unmodified black-box harnesses means models can be trained against the same tooling used in production, narrowing the train/deploy gap.