Saved in:
Bibliographic Details
Main Authors: Jiao, Zihao, Sha, Mengyi, Zhang, Haoyu, Jiang, Xinyu, Qi, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.10958
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914837389377536
author Jiao, Zihao
Sha, Mengyi
Zhang, Haoyu
Jiang, Xinyu
Qi, Wei
author_facet Jiao, Zihao
Sha, Mengyi
Zhang, Haoyu
Jiang, Xinyu
Qi, Wei
contents Existing operations research (OR) models and tools play indispensable roles in smart-city operations, yet their practical implementation is limited by the complexity of modeling and deficiencies in optimization proficiency. To generate more relevant and accurate solutions to users' requirements, we propose a large language model (LLM)-based agent ("City-LEO") that enhances the efficiency and transparency of city management through conversational interactions. Specifically, to accommodate diverse users' requirements and enhance computational tractability, City-LEO leverages LLM's logical reasoning capabilities on prior knowledge to scope down large-scale optimization problems efficiently. In the human-like decision process, City-LEO also incorporates End-to-end (E2E) model to synergize the prediction and optimization. The E2E framework be conducive to coping with environmental uncertainties and involving more query-relevant features, and then facilitates transparent and interpretable decision-making process. In case study, we employ City-LEO in the operations management of e-bike sharing (EBS) system. The numerical results demonstrate that City-LEO has superior performance when benchmarks against the full-scale optimization problem. With less computational time, City-LEO generates more satisfactory and relevant solutions to the users' requirements, and achieves lower global suboptimality without significantly compromising accuracy. In a broader sense, our proposed agent offers promise to develop LLM-embedded OR tools for smart-city operations management.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10958
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle City-LEO: Toward Transparent City Management Using LLM with End-to-End Optimization
Jiao, Zihao
Sha, Mengyi
Zhang, Haoyu
Jiang, Xinyu
Qi, Wei
Optimization and Control
Computation and Language
Multiagent Systems
Existing operations research (OR) models and tools play indispensable roles in smart-city operations, yet their practical implementation is limited by the complexity of modeling and deficiencies in optimization proficiency. To generate more relevant and accurate solutions to users' requirements, we propose a large language model (LLM)-based agent ("City-LEO") that enhances the efficiency and transparency of city management through conversational interactions. Specifically, to accommodate diverse users' requirements and enhance computational tractability, City-LEO leverages LLM's logical reasoning capabilities on prior knowledge to scope down large-scale optimization problems efficiently. In the human-like decision process, City-LEO also incorporates End-to-end (E2E) model to synergize the prediction and optimization. The E2E framework be conducive to coping with environmental uncertainties and involving more query-relevant features, and then facilitates transparent and interpretable decision-making process. In case study, we employ City-LEO in the operations management of e-bike sharing (EBS) system. The numerical results demonstrate that City-LEO has superior performance when benchmarks against the full-scale optimization problem. With less computational time, City-LEO generates more satisfactory and relevant solutions to the users' requirements, and achieves lower global suboptimality without significantly compromising accuracy. In a broader sense, our proposed agent offers promise to develop LLM-embedded OR tools for smart-city operations management.
title City-LEO: Toward Transparent City Management Using LLM with End-to-End Optimization
topic Optimization and Control
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2406.10958