The field of distributed optimization and control in multi-agent systems is moving towards more adaptive and robust methods. Researchers are exploring the use of machine learning and neural networks to improve the performance and efficiency of distributed algorithms. One notable direction is the development of meta-learning frameworks that can adapt to diverse tasks and agent configurations. Another area of focus is the enhancement of robustness in centralized transportation systems through online tuning and learning. Noteworthy papers include: Learning to Coordinate, which proposes a general framework for meta-learning hyperparameters in distributed trajectory optimization, and Learning to accelerate distributed ADMM using graph neural networks, which shows that distributed ADMM iterations can be naturally represented within the message-passing framework of graph neural networks.