dongsheng zhu's picture

dongsheng zhu

dongsheng

·

AI & ML interests

nlp, cv

Recent Activity

authored a paper about 11 hours ago

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

upvoted a paper about 19 hours ago

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

updated a dataset about 22 hours ago

dongsheng/ToolMaze

View all activity

Organizations

Collections 1

Papers 6

arxiv:2606.05806

arxiv:2603.25040

arxiv:2511.08487

arxiv:2508.15763

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 • 1 • 1

datasets 2

dongsheng/ToolMaze

Updated about 19 hours ago • 1k • 4

dongsheng/DTA-Tool

Viewer • Updated Jan 23, 2025 • 21.3k • 37 • 6