dongsheng zhu

dongsheng

·

AI & ML interests

nlp, cv

Recent Activity

authored a paper 3 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

upvoted a paper 6 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

submitted a paper about 2 months ago

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

View all activity

Organizations

Collections 1

Papers 7

arxiv:2607.13705

arxiv:2606.05806

arxiv:2603.25040

arxiv:2511.08487

spaces 2

BigCodeBench Evaluator

Fundus Img

models 3

dongsheng/DTA_llama2_13b

Updated Feb 26, 2025 • 2

dongsheng/DTA_llama3_8b

8B • Updated Jan 24, 2025 • 4

dongsheng/DTA_llama2_7b

Updated Jan 23, 2025 • 2 • 1

datasets 2

dongsheng/ToolMaze

Updated Jun 5 • 245 • 4

dongsheng/DTA-Tool

Viewer • Updated Jan 23, 2025 • 21.3k • 19 • 6