Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.12559v1</id>\n    <title>Large Language Models as Delivery Rider: Generating Instant Food Delivery Riders' Routing Decision with LLM Agent Framework</title>\n    <updated>2026-03-13T01:41:31Z</updated>\n    <link href='https://arxiv.org/abs/2603.12559v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.12559v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='physics.soc-ph'/>\n    <published>2026-03-13T01:41:31Z</published>\n    <arxiv:comment>Proceedings of the 3rd International Conference on Urban Science and Intelligence</arxiv:comment>\n    <arxiv:primary_category term='physics.soc-ph'/>\n    <author>\n      <name>Chengbo Zhang</name>\n    </author>\n    <author>\n      <name>Zuopeng Xiao</name>\n    </author>\n  </entry>"
}