Yirong Zeng

yrzeng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers 4 months ago

Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following

Paper • 2601.04954 • Published Jan 8 • 1

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch

Paper • 2511.01934 • Published Nov 2, 2025 • 1

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

Paper • 2505.07512 • Published May 12, 2025

Boosting Tool Use of Large Language Models via Iterative Reinforced Fine-Tuning

Paper • 2501.09766 • Published Jan 15, 2025 • 1