Model Releases
Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It launches with two core designs: 🥳 - Elastic …
Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It launches with two core designs: 🥳 - Elastic Scheduler: reallocates GPUs between rollout & training as dem
Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ 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. - Trajectory Processor: turns branching executions (compaction, sub-agents, retries) into prefix-shared trajectory trees with bounded, deduplicated training samples. Partial progress after timeout still gets scored. Scaled to Qwen3.8-2.4T-A95B with ~700K tokens per rollout, QwenGyre lifts NL2RepoBench from 52.5% to 58.5% in 48 steps, cutting end-to-end training time by ~44% vs Async. 🔗 Read the paper: https://arxiv.org/abs/2609.33848
Related
- Qwen released QwenGyre - RL framework for training AI agents on extremely long complex tasks
- QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
- KLong: Training LLM Agent for Extremely Long-horizon Tasks
Source: Qwen (X) | 2026-10-12