A Details on Tasks and Experiments

For the first time, our research introduces continual learning for abstract logical concepts, which mimics the process of humans acquiring higher-order learning abilities. This moves away from the traditional CL approach centered around images and considers a new direction that CL should ultimately strive for. Algorithmic reasoning tasks are fundamentally different from image data in their abstract and logical nature. The discontinuity of input data, the necessity for generalization regarding out-of-distribution samples, and the inability to use data augmentation or mix-up techniques present the need for new CL algorithms that differ from existing methodologies. We hope that future research will further explore methodologies that effectively leverage these unique characteristics of AR.