Our paper on "Instance-Based Opponent Action Prediction in Soccer Simulation Using Boundary Graphs" has been accepted for publication and presentation at the RoboCup Symposium 2022. The ability to correctly anticipate an opponent's next action in real-time adversarial environments depends on both, the amount of collected observations of that agent's behavior as well as on the capability to incorporate new knowledge into the opponent model easily. In this paper, we present a novel approach to instance-based action prediction that utilizes graph-based structures for the efficiency of retrieval, that scales logarithmically with the amount of training data, and that can be used in an online and anytime manner. We apply this algorithm to the use case of predicting a dribbling agent's next action in Soccer Simulation 2D. You can find the full paper here.