RideAgent: An LLM-Enhanced Optimization Framework for Automated Taxi Fleet Operations

TL;DR

RideAgent leverages large language models to interpret managerial objectives, formulate optimization problems, and accelerate electric ride-hailing fleet management, significantly reducing computation time while maintaining solution quality.

Contribution

The paper introduces RideAgent, a novel LLM-powered framework that automates and enhances fleet management by translating natural language objectives into optimization models and guiding solution strategies.

Findings

LLM achieves 86% similarity to standard formulations in zero-shot setting.

Variable fixing reduces computation time by 53.15% with minimal optimality gap.

Outperforms five cutting plane methods by 42.3% time reduction.

Abstract

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, an LLM-powered agent framework that automates and enhances electric ride-hailing fleet management. First, an LLM interprets natural language queries from fleet managers 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 53.15% compared to solving the full MIP with only a 2.42% 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 robust and adaptive automated framework for objective modeling and accelerated optimization. This framework empowers non-expert fleet managers to personalize operations and improve urban transportation system performance.