Sana
Ebrahimi
Ledene

I am a PhD candidate in Computer Science at the University of Illinois Chicago. My work sits at the intersection of Responsible and Reliable AI, with a special focus on Large Language Model (LLM) multi-agent systems. I design and evaluate orchestration methods, debate, role assignment, voting, and runtime supervision that maintain performance while strengthening accountability and influence measurement. I am interested in fairness in agent societies, robustness under adversarial or shifting conditions, and practical tools that make complex LLM teams safer and easier to trust.