Shin Hwei Tan

3 papers · Latest: April 23, 2026

Ethics Testing: Proactive Identification of Generative AI System Harms

This paper introduces "ethics testing," a novel approach to systematically identify and mitigate software harms in content generated by Generative AI systems.

2604.22089Apr 23, 2026

Software Engineering

Dissecting Bug Triggers and Failure Modes in Modern Agentic Frameworks: An Empirical Study

This paper empirically dissects 409 bugs in modern agentic AI frameworks, identifying unique failure modes and root causes to improve reliability.

2604.08906Apr 10, 2026

Software Engineering

Investigating Code Reuse in Software Redesign: A Case Study

This paper investigates code reuse in software redesign, identifying challenges and proposing a clone detection approach to improve migration efficiency.

2604.07919Apr 9, 2026

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.