Showing cs.SEShow all
3 papers · 1 filter
cs.SE2026
Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data
Xin Li, Rami Bahsoon, Tao Chen
Agentic workflows combine large language models with planning, memory, tools, execution environments, and iterative feedback. Their failures are difficult to diagnose because the s…
cs.SE2026
Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety
Nuwayyir Almohammadi, Rami Bahsoon, Tao Chen
Requirements engineers for agentic-AI domains face challenges in evaluating, specifying, and operationalizing safe autonomy. Mainstream frameworks, such as Goal-Oriented Requiremen…
cs.SE2026
On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems
Muhammad Tukur, Hayatullahi B. Adeyemo, Tao Chen +5
Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education. While these systems offer powe…