The checkpoints of the models trained with Youtu-Agent RL for Code/Math and Search tasks.
-
yolay/Youtu-Agent-RL-Search-Qwen2.5-7B
Text Generation • 8B • Updated • 17 • 1 -
yolay/Youtu-Agent-RL-Maths-Qwen2.5-7B
Text Generation • 8B • Updated • 5 -
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Paper • 2512.24615 • Published • 108