AI agents are rapidly evolving, from the early efforts to simulate human cognition and social behavior, to sophisticated multi-agent systems that can act as practical collaborators in everyday work. Building on nearly 75 years of AI and NLP research, today’s AI agents can plan, reason, communicate, and even coordinate. This talk explores the growing capabilities of AI agents as both mirrors and extensions of human cognition and behavior. I will discuss advances in multi-agent frameworks that simulate social reasoning, cooperation, and emergent communication, and explore how these capabilities are being translated into workplace applications supporting brainstorming, narrative development, and research design.