Unverified50% confidenceReleaseExact time
The Qwen team has open-sourced QwenGyre, an elastic reinforcement learning framework for ultra-long-horizon agent training (XLong agent training).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedQwen 3 is an open-source large language model series released by Alibaba's Tongyi Lab, featuring hybrid reasoning modes and reinforcement learning post-training capabilities.76% similarUnverifiedThe Qwen series of models was developed by Alibaba's Tongyi Lab.71% similarUnverifiedThe Tongyi Qianwen (Qwen) series has chosen an open-source path.66% similarUnverifiedThe off-policy distillation experiment uses Qwen3 0.6B as the student model and Qwen3 4B as the teacher model.66% similarUnverifiedResearchers tested two technical approaches on the Qwen3-14B model: directly training the model to learn when to answer, and training an independent answer selector60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006613API
curl https://kongchang.com/api/v1/knowledge/claims/1006613MCP
get_claim(id=1006613)