The main topic of this chapter is the introduction of the concept of the fusion of real and virtual worlds creating augmented virtuality by using mobile agents and agent-based simulation technologies. Virtual worlds are created by simulation or by digital games. Socio-technical systems are characterised by interactions of (1) human-to-human (initiated by a human), (2) human-to-machine (initiated by a human), (3) machine-to-human (initiated by a machine, for example a chat bot) and (4) machine-to-machine (initiated by a machine) interfaces. Modelling of such complex interaction networks is difficult. The simulation of social ensemble behaviour requires simplification of interactions and individual behaviour. Commonly, simulations are performed with a number of entities (humans, machines, etc.) in a sandbox world significantly below real population sizes. Agent-based modelling (ABM) is a suitable behaviour model for simulation. Simulation worlds are commonly closed and rely on artificial sensory information generated by the simulator program or using data collected offline (? field studies). A new simulation paradigm providing augmented virtuality is introduced providing the coupling and integration of mobile crowd sensing and social data mining in agent-based simulation worlds. The simulation world interacts with real-world environments, humans, machines, and other virtual worlds in real time using agent-based modelling and computation. Agents can represent artificial humans, bots, and machines, and agents can be used for distributed mobile computing, for example crowd sensing. The concept of agent-based virtual sensors and sensor aggregation is introduced with examples from crowd sensing applications.