ToolRM - a RioLee Collection

RioLee 's Collections

ToolRM

ToolRM

updated 5 days ago

ToolRM: Towards Agentic Tool-Use Reward Modeling

One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning

Paper • 2510.26167 • Published Oct 30, 2025 • 1
RioLee/ToolRM-Gen-Qwen3-4B-Thinking-2507

Text Generation • 4B • Updated 5 days ago • 8
RioLee/ToolPref-Pairwise-30K

Viewer • Updated 5 days ago • 89.5k • 95 • 2
RioLee/TRBench-BFCL

Viewer • Updated 5 days ago • 11.9k • 21 • 1