Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper
• 2505.16410 • Published
• 58
Tool-Star
Tool-Star is a reinforcement learning-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasonin
-
-
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 101 • 10 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 78 • 5 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 7 • 2 -
dongguanting/Tool-Star-Qwen-3B
Text Generation • 3B • Updated • 7 • 5 -
dongguanting/Tool-Star-Qwen-1.5B
Text Generation • 2B • Updated • 21 • 2 -
dongguanting/Tool-Star-Qwen-0.5B
Text Generation • 0.6B • Updated • 4 • 1