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. Note to Practitioners—The management of electric ride-hailing fleets, particularly taxi pre-allocation and dynamic pricing during peak hours, poses complexities for service providers aiming to balance supply with urban demand. Translating diverse business objectives—such as maximizing revenue or enhancing taxi utilization—into actionable strategies can be challenging for operators without optimization expertise. This work introduces RideAgent, a Large Language Model (LLM)-based framework that automates and simplifies these core operational decisions. RideAgent assists fleet operators by interpreting their objectives from natural language into formal optimization goals. It then uses historical data to accelerate the computation of pre-allocation and pricing decisions. For fleet management practitioners, RideAgent offers a more intuitive and customizable approach to operations: it enables the incorporation of specific managerial insights into objective formulation and significantly reduces the time to generate high-quality operational decisions. Our findings show that solution times can be reduced by over 50% while maintaining near-optimal results. This allows for more agile and personalized decision-making. By lowering the technical barrier to using advanced optimization, RideAgent empowers a broader range of personnel to contribute to efficient fleet management. As the ride-hailing industry adopts AI-driven solutions, RideAgent provides a practical pathway for integrating advanced natural-language understanding and automated optimization into daily fleet operations, improving urban mobility services.