Agentic Reinforced Policy Optimization
Paper
•
2507.19849
•
Published
•
140
ARPO
The official datasets and model checkpoints of ARPO
-
-
dongguanting/Qwen3-8B-ARPO-DeepSearch
8B • Updated • 30 • 1 -
dongguanting/Qwen3-14B-ARPO-DeepSearch
Text Generation • 15B • Updated • 60 • 4 -
dongguanting/Qwen2.5-7B-ARPO
Text Generation • 8B • Updated • 67 • 2 -
dongguanting/Llama3.1-8B-ARPO
Text Generation • 8B • Updated • 16 • 1 -
dongguanting/Qwen2.5-3B-ARPO
Text Generation • 3B • Updated • 42 • 1 -
dongguanting/ARPO-SFT-54K
Viewer • Updated • 54.6k • 692 • 8 -
dongguanting/ARPO-RL-Reasoning-10K
Viewer • Updated • 10k • 320 • 2 -
dongguanting/ARPO-RL-DeepSearch-1K
Viewer • Updated • 1.07k • 273 • 3