… agent for a wide variety of tasks (language modelling, playing Atari games, robotic control,
image captioning), we provide a generalist agent for a diverse set of algorithmic domains, …

… We find that ChatGPT outperforms specialist GNN models, … discussion about learning
algorithms with neural networks. … small specialist models, like neural algorithmic reasoners, is …

… specialist. The sensitivity of the model was 91% and specificity was 100%. The estimated κ
score was 0.950. Conclusions: This is the first study based on an artificial neural … algorithms …

… our neural model on relevant algorithms before training it on CO instances. Our results
demonstrate that by using this learning … A generalist neural algorithmic learner. In B. Rieck and R. …

… (2022) expand on this concept by building a generalist neural algorithmic learner that can …
of neural algorithmic reasoning on graphs. Specifically, we target learning of graph algorithms …

… the benefits of both classical algorithms and neural networks by executing algorithms using
… a step towards transferable algorithmic knowledge [16] and generalist algorithmic learners [9]…

… to learn algorithms … learning algorithms step-by-step, giving models access to all intermediate
steps of the original algorithm. In this work, we instead focus on learning neural algorithmic …

… via neural algorithmic reasoning We address this challenge and present the first learning-based …
Our relaxed formulation allows us, for the first time, to apply end-to-end learning to the …

… Classical algorithms often pose a bottleneck to information … Machine learning and neural
networks (NNs) in particular … execute algorithms is the objective of neural algorithmic reasoning […

… the benefits of both classical algorithms and neural networks by executing algorithms using
… a step towards transferable algorithmic knowledge [16] and generalist algorithmic learners [9]…