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
about 21 hours ago
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn
Reinforcement Learning
upvoted
a
paper
about 21 hours ago
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs
via Bi-Mode Annealing and Reinforce Learning
upvoted
a
paper
about 21 hours ago
A Survey of Scientific Large Language Models: From Data Foundations to
Agent Frontiers
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 • 57 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 268 • 8 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 127 • 4 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 20 • 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 • 57 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 268 • 8 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 127 • 4 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 20 • 2
models
10
dongguanting/Qwen2.5-7B-ARPO
Text Generation
•
8B
•
Updated
•
72
•
2
dongguanting/Llama3.1-8B-ARPO
Text Generation
•
8B
•
Updated
•
16
•
1
dongguanting/Qwen2.5-3B-ARPO
Text Generation
•
3B
•
Updated
•
22
•
1
dongguanting/Qwen3-14B-ARPO-DeepSearch
Text Generation
•
15B
•
Updated
•
63
•
4
dongguanting/Qwen3-8B-ARPO-DeepSearch
8B
•
Updated
•
31
•
1
dongguanting/Tool-Star-Qwen-7B
Text Generation
•
8B
•
Updated
•
20
•
2
dongguanting/RAG-Critic-3B
Text Generation
•
3B
•
Updated
•
20
•
3
dongguanting/Tool-Star-Qwen-0.5B
Text Generation
•
0.6B
•
Updated
•
10
•
1
dongguanting/Tool-Star-Qwen-1.5B
Text Generation
•
2B
•
Updated
•
24
•
2
dongguanting/Tool-Star-Qwen-3B
Text Generation
•
3B
•
Updated
•
20
•
5
datasets
11
dongguanting/ARPO-SFT-54K
Viewer
•
Updated
•
54.6k
•
528
•
9
dongguanting/ARPO-RL-Reasoning-10K
Viewer
•
Updated
•
10k
•
223
•
3
dongguanting/ARPO-RL-DeepSearch-1K
Viewer
•
Updated
•
1.07k
•
161
•
4
dongguanting/RAG-Error-Critic-100K
Viewer
•
Updated
•
100k
•
19
•
2
dongguanting/Tool-Star-SFT-54K
Viewer
•
Updated
•
54k
•
268
•
8
dongguanting/Multi-Tool-RL-10K
Viewer
•
Updated
•
10k
•
127
•
4
dongguanting/RAG-QA-40K
Viewer
•
Updated
•
32.8k
•
17
•
2
dongguanting/ShareGPT-12K
Viewer
•
Updated
•
12.9k
•
28
•
1
dongguanting/VIF-RAG-QA-110K
Viewer
•
Updated
•
111k
•
43
•
7
dongguanting/DotamathQA
Viewer
•
Updated
•
574k
•
52
•
2