Chen Yang

flust's activity

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

authored 4 papers 1 day ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 3 days ago • 16

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model

Paper • 2607.22083 • Published 17 days ago • 7

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

Paper • 2602.13367 • Published Feb 13 • 37

ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset

Paper • 2511.15718 • Published Nov 12, 2025 • 2

updated a collection 1 day ago

Nanbeige4.2-3B

Collection

6 items • Updated 1 day ago • 6

upvoted a paper 1 day ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 3 days ago • 16

New activity in InternScience/Agents-A1-4B 7 days ago

Could you clarify whether "retry@5" is equivalent to pass@5?

3

#3 opened 9 days ago by

flust

updated a model 16 days ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated 11 days ago • 43.2k • 693

liked a model 22 days ago

Nanbeige/Nanbeige4.2-3B

Text Generation • 4B • Updated 11 days ago • 43.2k • 693

updated a model 5 months ago

Nanbeige/Nanbeige4.1-3B

Text Generation • 4B • Updated Mar 25 • 18.8k • • 1.16k

liked a dataset 6 months ago

Nanbeige/ToolMind-Web-QA

Preview • Updated Feb 19 • 483 • 62

updated a dataset 6 months ago

Nanbeige/ToolMind-Web-QA

Preview • Updated Feb 19 • 483 • 62

updated a model 6 months ago

Nanbeige/ToolMind-Web-3B

Text Generation • Updated Feb 12 • 164 • 29

published a dataset 6 months ago

Nanbeige/ToolMind-Web-QA

Preview • Updated Feb 19 • 483 • 62

liked a model 6 months ago

Nanbeige/Nanbeige4.1-3B

Text Generation • 4B • Updated Mar 25 • 18.8k • • 1.16k

upvoted a paper 6 months ago

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published Feb 3 • 41

liked a model 7 months ago

Nanbeige/ToolMind-Web-3B

Text Generation • Updated Feb 12 • 164 • 29

published a model 7 months ago

Nanbeige/ToolMind-Web-3B

Text Generation • Updated Feb 12 • 164 • 29

New activity in meituan-longcat/LongCat-Flash-Thinking-2601 7 months ago

Is Heavythink >= pass@n ?

👀 1

#3 opened 7 months ago by

flust

updated a dataset 7 months ago

Nanbeige/ToolMind

Viewer • Updated Jan 9 • 369k • 2.52k • 169