How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
Paper
•
2511.08487
•
Published
•
3
dongsheng zhu
dongsheng
AI & ML interests
nlp, cv
Recent Activity
liked
a model
9 days ago
internlm/Intern-S1-Pro
authored
a paper
20 days ago
How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
Organizations
authored
a
paper
20 days ago
authored
3
papers
6 months ago
Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
Paper
•
2501.12432
•
Published
•
1
Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
Paper
•
2508.15754
•
Published
•
4
Intern-S1: A Scientific Multimodal Foundation Model
Paper
•
2508.15763
•
Published
•
269