Amin Samadi

I'm a Ph.D. candidate in the Language and Learning Analytics Lab at UC Irvine, advised by Dr. Nia Nixon, and currently an AI Scientist Intern at ROI-AI in San Francisco, where I build production LLM agent systems. I study how humans and intelligent systems learn, collaborate, and make sense of complex problems together—bringing together AI, cognitive science, and human–computer interaction. My dissertation research on human–AI collaboration in teams received the UCI School of Education's Vandell Dissertation Research Award.

I lead TRAIL (Team Research and AI Integration Lab), a platform that simulates team problem-solving with configurable AI teammates to study how personality, trust, and communication shape human–AI collaboration.

Research Focus

Human–AI Alignment in Teams

How AI teammates align with human intentions through persona design, behavioral tuning, and adaptive proactivity. TRAIL agents vary in persona traits, behavioral parameters, and proactivity settings—advancing a framework of socio-cognitive alignment.

Cognitive and Social Dynamics

Using temporal, linguistic, and behavioral modeling to analyze how reasoning and shared understanding unfold in human and human–AI teams.

HCI for AI Systems

Designing interfaces that make AI collaboration visible—dashboards for interaction memory, reflection prompts, and adaptive feedback loops.

Model Welfare and Reflective AI

How AI systems reason about their own limitations, uncertainty, and ethical alignment during long-term collaboration.

Selected Publications