Cite
Notes
Only stored in your browser.
Attribution
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
arXiv 2026
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
arXiv 2025
from 2 papers
Jian Kang
Jieyu Zhao
Linxin Song
Taiwei Shi
Jiate Li
Jieyu Zhang
Nicholas Meade
Rahul Gupta
Ryotaro Shimizu
Siva Reddy