# Alibaba’s QwenGyre speeds up long-horizon agent training by up to 1.85x

Digest AI · Research · published 2026-10-12T21:41:50Z

Canonical: https://digestai.news/story/alibabas-qwengyre-speeds-up-long-horizon-agent-training-by-up-to-1-85x

## Summary

Alibaba’s Qwen team introduced **QwenGyre**, an elastic reinforcement learning framework designed for extreme-long-horizon agent training. It targets tasks running for hours and processing nearly **1M tokens** per rollout, tested on Qwen’s **3.6 122B** and **3.8 2.4T** models. QwenGyre improves efficiency by dynamically reallocating idle GPUs between rollouts and training, reducing idle time and handling branching agent histories without inflating training costs.

The framework achieves **1.38x to 1.78x speedups** over Async and **1.21x to 1.85x** over Colocate, with a **1.85x end-to-end speedup** on TerminalBench. On NL2RepoBench, QwenGyre improved performance from **52.5%** to **58.5%** in 48 steps. However, no public code release is linked, and performance varies—some runs saw minimal gains due to timeouts. The system relies on multi-node GPU clusters, with the **2.4T model** using **192 nodes** (4 cells of 48).

## Key points

- QwenGyre cuts training time by up to 1.85x over Colocate for long-horizon agent tasks
- Tested on Qwen 3.6 122B (24–32 nodes) and Qwen 3.8 2.4T (192 nodes) with ~700K tokens per rollout
- No public code release, but NL2RepoBench performance rose from 52.5% to 58.5% in 48 steps

## Why it matters

Faster training for long-horizon agents could reduce costs for tasks like codebase generation, but no public tools or benchmarks confirm real-world impact yet.

## Sources

1. [Alibaba Qwen Introduces QwenGyre: Elastic Reinforcement Learning RL for XLong-Horizon Agents](https://marktechpost.com/2026/10/12/alibaba-qwen-introduces-qwengyre-elastic-reinforcement-learning-rl-for-xlong-horizon-agents) (MarkTechPost, 2026-10-12)

Part of the developing story: [AI Audio Arms Race Accelerates with Low‑Cost Real‑Time Voice](https://digestai.news/thread/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing) (5 stories)

## Cite

Digest AI, "Alibaba’s QwenGyre speeds up long-horizon agent training by up to 1.85x", 12 October 2026, https://digestai.news/story/alibabas-qwengyre-speeds-up-long-horizon-agent-training-by-up-to-1-85x

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/alibabas-qwengyre-speeds-up-long-horizon-agent-training-by-up-to-1-85x.json