# Alibaba — Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨

- Company: Alibaba (alibaba.com)
- Announced: 2026-10-12T13:11:37+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://x.com/Alibaba_Qwen/status/2109633085658808515
- Record: https://forck.live/items/24045-introducing-qwengyre-bringing-elastic-rl-to-extreme-long-horizon-xlong-agent
- Models affected: Qwen3.8-2.4T-A95B

Alibaba's Qwen team introduced QwenGyre, an elastic reinforcement learning system for extreme-long-horizon agent training that reallocates GPUs between rollout and training without interrupting live executions. The Elastic Scheduler achieves up to 1.85 times speedup over Colocate and 1.78 times over Async by shifting compute resources as demand changes. A Trajectory Processor converts branching executions into prefix-shared trajectory trees with bounded, deduplicated training samples, scoring partial progress even after timeout. Scaled to Qwen3.8-2.4T-A95B with roughly 700K tokens per rollout, QwenGyre lifted NL2RepoBench from 52.5 percent to 58.5 percent in 48 steps while cutting end-to-end training time by about 44 percent versus Async.

## Evidence

Verbatim from https://x.com/Alibaba_Qwen/status/2109633085658808515:

> It launches with two core designs: Elastic Scheduler: reallocates GPUs between rollout & training as demand shifts—live executions never interrupted. Up to 1.85× speedup over Colocate, 1.78× over Async.

---

Record: https://forck.live/items/24045-introducing-qwengyre-bringing-elastic-rl-to-extreme-long-horizon-xlong-agent
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md