The field of vehicle routing and ridesharing systems is experiencing significant advancements with the integration of machine learning and artificial intelligence. Researchers are exploring new approaches to improve the efficiency and effectiveness of algorithms used in these systems. Notably, the use of explainable AI and feature importance analysis is becoming increasingly popular in developing guidance mechanisms for metaheuristic algorithms. Additionally, hybrid optimization solvers that combine machine learning models with traditional optimization techniques are showing promising results in solving complex problems such as the Capacitated Vehicle Routing Problem. Furthermore, the predictability and explainability of pre-request passenger waiting time in ridesharing systems is being investigated, with novel models being proposed to improve the accuracy of waiting time predictions. Overall, these advancements have the potential to significantly impact the field, enabling more efficient and effective solutions to complex problems. Noteworthy papers include: Study of Robust Features in Formulating Guidance for Heuristic Algorithms for Solving the Vehicle Routing Problem, which proposes a unified framework for ranking feature impact across different scenarios. POMO+: Leveraging starting nodes in POMO for solving Capacitated Vehicle Routing Problem, which improves the POMO method by leveraging initial nodes to find a solution in a more informed way. Hybrid Node-Destroyer Model with Large Neighborhood Search for Solving the Capacitated Vehicle Routing Problem, which proposes an iterative learning hybrid optimization solver that integrates a machine learning hybrid model with a Large Neighborhood Search operator. A First Look at Predictability and Explainability of Pre-request Passenger Waiting Time in Ridesharing Systems, which proposes a novel feature interaction-based XGBoost model to predict waiting time without knowing the assigned driver information.