Large Language Models as Delivery Rider: Generating Instant Food Delivery Riders' Routing Decision with LLM Agent Framework

TL;DR

This paper introduces LLM-DR, a novel framework using Large Language Models to simulate heterogeneous rider decision-making in instant food delivery, enabling high-fidelity mobility system analysis.

Contribution

It presents a new LLM-based agent framework with empirically-grounded personas and reasoning-based routing for simulating delivery rider behavior.

Findings

Successfully models complex rider behaviors in real-world data

Reveals how rider workforce composition affects system outcomes

Demonstrates the potential of LLMs in mobility system simulation

Abstract

The utilization of Large Language Models (LLMs) to power human-like agents has shown remarkable potential in simulating individual mobility pattern. However, a significant gap remains in modeling cohorts of agents in dynamic and interactive systems where they must take strategic routing decisions to response mobility-specific task. To bridge this gap, we introduce LLM-DR, a novel agent framework designed to simulate the heterogeneous decision-making of riders in the on-demand instant delivery task scenario. Our framework is founded on two principles: 1) Empirically-grounded personas, where we use unsupervised clustering on a large-scale, real-world trajectory dataset to identify four distinct rider work strategies; and 2) Reasoning-based routing process, where each persona is instantiated as an LLM agent that employs a structured Chain-of-Thought (CoT) process to make human-like routing choices. This framework enables the construction of high-fidelity simulations to investigate how the strategic composition of a rider workforce influences system-level outcomes regarding their mobility pattern. We validate our framework on an real-world instant deliver order datasets, demonstrating its capacity to model complex rider behavior in an interactive market scenario. This work provides pioneering findings in agentic mobility system empowered by LLM.