dongsheng zhu

dongsheng's activity

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

authored a paper 9 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Paper • 2607.13705 • Published 15 days ago • 44

upvoted a paper 12 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Paper • 2607.13705 • Published 15 days ago • 44

submitted a paper to Daily Papers about 2 months ago

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Paper • 2606.05806 • Published Jun 4 • 23

authored a paper about 2 months ago

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Paper • 2606.05806 • Published Jun 4 • 23

upvoted a paper about 2 months ago

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Paper • 2606.05806 • Published Jun 4 • 23

updated a dataset about 2 months ago

dongsheng/ToolMaze

Updated Jun 5 • 244 • 4

liked a dataset about 2 months ago

dongsheng/ToolMaze

Updated Jun 5 • 244 • 4

upvoted a collection about 2 months ago

Intern-S2

Collection

4 items • Updated 12 days ago • 23

published a dataset about 2 months ago

dongsheng/ToolMaze

Updated Jun 5 • 244 • 4

liked a model 2 months ago

internlm/Intern-S2-Preview

Image-Text-to-Text • 36B • Updated May 29 • 16.1k • 115

authored a paper 4 months ago

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 134

upvoted a paper 4 months ago

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 134

liked a model 6 months ago

internlm/Intern-S1-Pro

Image-Text-to-Text • Updated Mar 30 • 357k • 279

authored a paper 6 months ago

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity

Paper • 2511.08487 • Published Nov 11, 2025 • 3

upvoted a paper 6 months ago

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity

Paper • 2511.08487 • Published Nov 11, 2025 • 3

liked a dataset 6 months ago

dongsheng/DTA-Tool

Viewer • Updated Jan 23, 2025 • 21.3k • 21 • 6

updated a Space 9 months ago

Sleeping

1

BigCodeBench Evaluator

🥇

1

New activity in inclusionAI/Ling-1T 9 months ago

How to deploy a model with function calling?

#16 opened 9 months ago by

dongsheng

authored 2 papers 11 months ago

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation

Paper • 2501.12432 • Published Jan 21, 2025 • 1

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Paper • 2508.15754 • Published Aug 21, 2025 • 4