Natural systems and processes have been one of the main sources of inspiration in the development of artificial intelligence. In particular, the phenomenon of emergent collective intelligence, that is the manifestation of a global intelligent behavior from the interactions of simple agents, has been one of the main inspirations in my research. In this talk, I will give some examples where I explored this idea in simulations of various types of collective systems. Specifically, I will discuss the use of individual and social learning strategies to achieve optimum learning as a collective. I will further discuss another example that aims to facilitate the emergence of division of labor and cooperation based on the peer-to-peer agent interactions in collections of self-interested lifetime-learning individuals. These examples can have a significant impact in improving efficiency and efficacy of learning in multi-agent systems and contribute to the understanding in learning processes in nature.