Abstract: This paper identifies several key limitations in the representation, control, locomotion, and authoring of autonomous virtual humans that must be addressed to enter the new age of interactive virtual world applications. These limitations include simplified particle representations of agents which decouples control and locomotion, the lack of multi-modal perception in virtual environments, the need for multiple levels of control granularity, homogeneity in character animation, and monolithic agent architectures which cannot scale to complex multi-agent interactions and global narrative constraints. We present this broad perspective with the objective of providing the stimulus for an exciting new era of virtual human research.