Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. Without the involvement of manual behavior specification via code or reliance on a defined taxonomy of possible behaviors, the demonstrator specifies spatial motion of the agents over time, and retrieves agent-level parameters required to execute that motion. A framework for reproducing emergent behavior, given an abstract demonstration, is discussed in existing work. Our work extends that framework by addressing the variation in reproduced behavior over several executions of the framework. The cause for such variation is identified to be the capacity of training data to represent the demonstration. Addressing this problem produces more favorable (more similar to the demonstration) replicated emergent behaviors. Our work is evaluated using demonstrations and visual features as in the aforementioned work. Experimental results show an improvement in the coherence between demonstrated behavior, and the corresponding replicated behavior produced by the framework.