qualidea1217/HiPRAG-Dataset
Viewer • Updated • 221k • 22
HiPRAG
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
-
-
qualidea1217/Llama-3.2-3B-Instruct-PPO-HiPRAG
4B • Updated • 8 -
qualidea1217/Qwen2.5-3B-Instruct-GRPO-HiPRAG
3B • Updated • 137 -
qualidea1217/Qwen2.5-3B-Instruct-PPO-HiPRAG
3B • Updated • 21 -
qualidea1217/Qwen2.5-7B-Instruct-GRPO-HiPRAG
8B • Updated • 13 -
qualidea1217/Qwen2.5-7B-Instruct-PPO-HiPRAG
8B • Updated • 44 -
qualidea1217/Qwen2.5-3B-Instruct-PPO-HiPRAG-Lambda_p-0.2
3B • Updated • 8 -
qualidea1217/Qwen2.5-3B-Instruct-PPO-HiPRAG-Lambda_p-0.6
3B • Updated • 5 -
qualidea1217/Qwen2.5-3B-PPO-HiPRAG
3B • Updated • 9 -
qualidea1217/Qwen2.5-3B-Instruct-PPO-HiPRAG-Oversearch-Only
3B • Updated • 17 -
qualidea1217/Qwen2.5-3B-Instruct-PPO-HiPRAG-Undersearch-Only
3B • Updated • 4