The ToolRL model trained for tool use through GRPO
Cheng Qian
chengq9
AI & ML interests
Agent, Tool Learning
Recent Activity
authored a paper 2 days ago
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses authored a paper 2 days ago
ACCORD: Action-Conditioned Contextual Grounding for Language Agents authored a paper 2 days ago
Trimming the Long-Tail of Visual World Modeling Evaluation