The ToolRL model trained for tool use through GRPO
Cheng Qian
chengq9
AI & ML interests
Agent, Tool Learning
Recent Activity
upvoted a paper about 18 hours ago
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses submitted a paper about 18 hours ago
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses