2 papers
cs.CR2026
DelegateGuard: Purpose-Bound Capabilities for Delegated LLM Agent Workflows
Phat T. Tran-Truong, Ha Vo, Nhut Tran +2
\textbf{(Context)} LLM agents increasingly delegate subtasks while holding authority over sensitive data, creating confused-deputy risks: an injected delegate can exfiltrate data,…
cs.SE2026
Exploring the Reasoning Depth of Small Language Models in Software Architecture: A Multidimensional Evaluation Framework Towards Software Engineering 2.0
Ha Vo, Nhut Tran, Khang Vo +2
In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Archit…