The official datasets and model checkpoints of ARPO
KABI
dongguanting
AI & ML interests
Reasoning and Alignment for Large Language Models
Recent Activity
upvoted
a
paper
5 days ago
Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference
Learning
Organizations
Tool-Star is a reinforcement learning-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasonin
-
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 56 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 144 • 8 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 63 • 4 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 9 • 2
The official datasets and model checkpoints of ARPO
Tool-Star is a reinforcement learning-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasonin
-
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 56 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 144 • 8 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 63 • 4 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 9 • 2
models
10
dongguanting/Qwen2.5-7B-ARPO
Text Generation
•
8B
•
Updated
•
45
•
2
dongguanting/Llama3.1-8B-ARPO
Text Generation
•
8B
•
Updated
•
6
•
1
dongguanting/Qwen2.5-3B-ARPO
Text Generation
•
3B
•
Updated
•
15
•
1
dongguanting/Qwen3-14B-ARPO-DeepSearch
Text Generation
•
15B
•
Updated
•
134
•
5
dongguanting/Qwen3-8B-ARPO-DeepSearch
8B
•
Updated
•
55
•
2
dongguanting/Tool-Star-Qwen-7B
Text Generation
•
8B
•
Updated
•
9
•
2
dongguanting/RAG-Critic-3B
Text Generation
•
3B
•
Updated
•
4
•
3
dongguanting/Tool-Star-Qwen-0.5B
Text Generation
•
0.6B
•
Updated
•
1
•
1
dongguanting/Tool-Star-Qwen-1.5B
Text Generation
•
2B
•
Updated
•
53
•
2
dongguanting/Tool-Star-Qwen-3B
Text Generation
•
3B
•
Updated
•
5
•
5
datasets
11
dongguanting/ARPO-SFT-54K
Viewer
•
Updated
•
54.6k
•
269
•
10
dongguanting/ARPO-RL-Reasoning-10K
Viewer
•
Updated
•
10k
•
74
•
3
dongguanting/ARPO-RL-DeepSearch-1K
Viewer
•
Updated
•
1.07k
•
96
•
4
dongguanting/RAG-Error-Critic-100K
Viewer
•
Updated
•
100k
•
29
•
2
dongguanting/Tool-Star-SFT-54K
Viewer
•
Updated
•
54k
•
144
•
8
dongguanting/Multi-Tool-RL-10K
Viewer
•
Updated
•
10k
•
63
•
4
dongguanting/RAG-QA-40K
Viewer
•
Updated
•
32.8k
•
20
•
2
dongguanting/ShareGPT-12K
Viewer
•
Updated
•
12.9k
•
24
•
1
dongguanting/VIF-RAG-QA-110K
Viewer
•
Updated
•
111k
•
34
•
7
dongguanting/DotamathQA
Viewer
•
Updated
•
574k
•
33
•
2