Efficient management of electric ride-hailing fleets, particularly pre-allocation and pricing during peak periods to balance spatio-temporal supply and demand, is crucial for urban traffic efficiency. However, practical challenges include unpredictable demand and translating diverse, qualitative managerial objectives from non-expert operators into tractable optimization models. This paper introduces RideAgent, a Large Language Model (LLM)-powered agent framework that automates and enhances electric ride-hailing fleet management. First, an LLM interprets natural language queries from fleet operators to formulate corresponding mathematical objective functions. These user-defined objectives are then optimized within a Mixed-Integer Programming (MIP) framework, subject to the constraint of maintaining high operational profit. The profit itself is a primary objective, estimated by an embedded Random Forest (RF) model leveraging exogenous features. To accelerate the solution of this MIP, a prompt-guided LLM analyzes a small sample of historical optimal decision data to guide a variable fixing strategy. Experiments on real-world data show that the LLM-generated objectives achieve an 86% text similarity to standard formulations in a zero-shot setting. Following this, the LLM-guided variable fixing strategy reduces computation time by 60.22% compared to solving the full MIP with only a 2.96% average optimality gap. Moreover, this variable fixing strategy outperforms five cutting plane methods by 42.3% time reduction with minimal compromise to solution quality. RideAgent offers a reliable and scalable automated framework for objective modeling and accelerated optimization. This framework empowers non-expert fleet operators to personalize operations and improve urban transportation system performance.

In this paper, we consider the alignment between an upstream dimensionality reduction task of learning a low-dimensional representation of a set of high-dimensional data and a downstream optimization task of solving a stochastic program parameterized by said representation. In this case, standard dimensionality reduction methods (e.g., principal component analysis) may not perform well, as they aim to maximize the amount of information retained in the representation and do not generally reflect the importance of such information in the downstream optimization problem. To address this problem, we develop a prescriptive dimensionality reduction framework that aims to minimize the degree of suboptimality in the optimization phase. For the case where the downstream stochastic optimization problem has an expected value objective, we show that prescriptive dimensionality reduction can be performed via solving a distributionally-robust optimization problem, which admits a semidefinite programming relaxation. Computational experiments based on a warehouse transshipment problem and a vehicle repositioning problem show that our approach significantly outperforms principal component analysis with real and synthetic data sets.