J. Keung

Understanding Bugs in Model Context Protocol Development Frameworks: An Empirical Study

This study investigates bug symptoms, root causes, bug fixing challenges and patterns, and the effectiveness of LLM-based automated repair in MCP development frameworks, presenting the first large-scale empirical study of bugs in MCP development frameworks.

FedDC: Efficient protection scheme based on chaotic system in federated learning

Designing Psychologically Safe AI Tutors for Students: An Emotion-Aware Post-Hoc Intervention for LLM-Assisted Learning

Large language models (LLMs) are increasingly integrated into students' learning processes, serving not only as cognitive tools for academic support but also as conversational partners that influence learners' emotional experience. However, existing LLM-based learning systems are not explicitly designed to account for...