The checkpoints of the models trained with Youtu-Agent RL for Code/Math and Search tasks.
🔄 In a Training Loop
Yulei Qin
yolay
AI & ML interests
Medical Imaging, Computer Vision,
Language Models
Recent Activity
authored a paper 2 days ago
CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent authored a paper 2 days ago
Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway SegmentationOrganizations
models 27
yolay/Youtu-Agent-RL-Maths-Qwen2.5-7B
Text Generation • 8B • Updated • 36 • 3
yolay/Youtu-Agent-RL-Search-Qwen2.5-7B
Text Generation • 8B • Updated • 42 • 1
yolay/SmartSnap-Qwen3-32B
33B • Updated • 16
yolay/SmartSnap-Qwen3-8B
8B • Updated • 14 • 1
yolay/SmartSnap-Qwen2.5-7B
8B • Updated • 24
yolay/SPEAR-SearchQA-Qwen2.5-14B
15B • Updated • 11
yolay/SPEAR-SearchQA-Qwen2.5-7B
8B • Updated • 25 • 1
yolay/SPEAR-ReTool-Qwen2.5-32B
33B • Updated • 10
yolay/SPEAR-ReTool-Qwen3-32B
33B • Updated • 2
yolay/SPEAR-ALFWorld-DrBoT-GRPO-1.5B
2B • Updated • 12