The collection of ToolSpace
KABI
dongguanting
AI & ML interests
Reasoning and Alignment for Large Language Models
Recent Activity
authored a paper about 7 hours ago
CoworkOS:Scaling Agent Coworkers for Real-world Automation upvoted a paper about 9 hours ago
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements upvoted a paper about 9 hours ago
CoworkOS:Scaling Agent Coworkers for Real-world AutomationOrganizations
The official datasets and model checkpoints of AEPO
-
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 109 -
dongguanting/Qwen3-8B-AEPO-DeepSearch
Text Generation • 8B • Updated • 27 • • 2 -
dongguanting/QwQ-32B-AEPO-DeepSearch
Text Generation • 33B • Updated • 24 • 2 -
dongguanting/Qwen3-14B-AEPO-DeepSearch
Robotics • 15B • Updated • 20 • 1
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 • 60 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 450 • 11 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 55 • 5 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 34 • 2
Paper: arXiv 2610.17953 · HF Papers · Code: RUC-NLPIR/Agent-Reflex
-
dongguanting/Agent-Reflex-SFT-54K
Viewer • Updated • 54.7k • 1.63k • 4 -
dongguanting/Agent-Reflex-8B
Text Generation • 8B • Updated • 696 • 5 -
dongguanting/Agent-Reflex-RL-2K
Viewer • Updated • 2.55k • 306 • 3 -
Agent-Reflex: Teaching Language Agents to Act Reflectively
Paper • 2610.17953 • Published • 36
The official datasets and model checkpoints of ARPO
The collection of ToolSpace
Paper: arXiv 2610.17953 · HF Papers · Code: RUC-NLPIR/Agent-Reflex
-
dongguanting/Agent-Reflex-SFT-54K
Viewer • Updated • 54.7k • 1.63k • 4 -
dongguanting/Agent-Reflex-8B
Text Generation • 8B • Updated • 696 • 5 -
dongguanting/Agent-Reflex-RL-2K
Viewer • Updated • 2.55k • 306 • 3 -
Agent-Reflex: Teaching Language Agents to Act Reflectively
Paper • 2610.17953 • Published • 36
The official datasets and model checkpoints of AEPO
-
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 109 -
dongguanting/Qwen3-8B-AEPO-DeepSearch
Text Generation • 8B • Updated • 27 • • 2 -
dongguanting/QwQ-32B-AEPO-DeepSearch
Text Generation • 33B • Updated • 24 • 2 -
dongguanting/Qwen3-14B-AEPO-DeepSearch
Robotics • 15B • Updated • 20 • 1
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 • 60 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 450 • 11 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 55 • 5 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 34 • 2