The future of self-driving cars, and smart homes require intelligent
agents that work intimately with people in a changing environment.
Instead of passively following orders given by users, an interactive
agent must actively collaborate with people through communication,
coordination, and user-adaptation. In this talk, I will present two
directions towards building agents that interact with the environment
and people. The first involves making predictions with incremental
inputs. I will focus on the application of simultaneous machine
translation and show how we can produce both accurate and prompt
translations. Then, I will present our work on building agents that
collaborate with people through goal-oriented conversation, as well as
agents that compete with people by modeling their behavior. I will
conclude by discussing several future directions.