2026
On Logical Extrapolation for Mazes with Recurrent and Implicit Networks
Brandon Knutson, Amandin Chyba Rabeendran, Michael Ivanitskiy, Jordan Pettyjohn, Cecilia Diniz Behn, Samy Wu Fung +1
AAAI 2026technical
Recent work suggests that certain neural network architectures — particularly recurrent neural networks (RNNs) and implicit neural networks (INNs) — are capable of logical extrapolation. When trained on easy instances of a task, these networks (henceforth: logical extrapolators) can generalize to mo