Renhao Li

RioLee's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in RioLee/ToolRM-Gen-Qwen3-4B-Thinking-2507 about 13 hours ago

Weak spot of the model

1

#1 opened about 18 hours ago by

NikolaiSkripko

updated a model 8 days ago

RioLee/ToolRM-Gen-Qwen3-4B-Thinking-2507

Text Generation • 4B • Updated 8 days ago • 23 • 1

updated 2 datasets 8 days ago

RioLee/TRBench-BFCL

Viewer • Updated 8 days ago • 11.9k • 21 • 2

RioLee/ToolPref-Pairwise-30K

Viewer • Updated 8 days ago • 89.5k • 97 • 3

upvoted a collection 2 months ago

ToolRM

Collection

ToolRM: Towards Agentic Tool-Use Reward Modeling • 6 items • Updated 8 days ago • 4

updated a collection 2 months ago

ToolRM

Collection

ToolRM: Towards Agentic Tool-Use Reward Modeling • 6 items • Updated 8 days ago • 4

authored 2 papers 2 months ago

CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation

Paper • 2406.07054 • Published Jun 11, 2024

One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning

Paper • 2510.26167 • Published Oct 30, 2025 • 2

published 2 datasets 2 months ago

RioLee/TRBench-BFCL

Viewer • Updated 8 days ago • 11.9k • 21 • 2

RioLee/ToolPref-Pairwise-30K

Viewer • Updated 8 days ago • 89.5k • 97 • 3

published a model 2 months ago

RioLee/ToolRM-Gen-Qwen3-4B-Thinking-2507

Text Generation • 4B • Updated 8 days ago • 23 • 1

updated a collection 2 months ago

ToolRM

Collection

ToolRM: Towards Agentic Tool-Use Reward Modeling • 6 items • Updated 8 days ago • 4

updated a collection 3 months ago

ToolRM

Collection

ToolRM: Towards Agentic Tool-Use Reward Modeling • 6 items • Updated 8 days ago • 4

liked a model 10 months ago

Qwen/QwQ-32B

Text Generation • 33B • Updated Mar 11, 2025 • 85k • • 2.88k

liked 2 models 12 months ago

deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27, 2025 • 352k • • 13k

deepseek-ai/DeepSeek-V3

Text Generation • 685B • Updated Mar 27, 2025 • 752k • • 4.02k

updated a collection about 1 year ago

CoEvol

Collection

Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation • 5 items • Updated Oct 26, 2024