An LLM-assisted real-time simulation framework for demand-responsive transport operations
- 1Department of Industrial and Management Engineering, Hanyang University, Seongdong-gu, Seoul, Republic of Korea
- 2Department of Industrial and Management Engineering, Hanyang University ERICA, Ansan, Gyeonggi-do, Republic of Korea
Abstract
Demand-responsive transport (DRT) is a dynamic service whose performance depends not only on dispatching and routing algorithms but also on how externally submitted demand is captured, interpreted, and incorporated into operations. Although prior studies have largely emphasized algorithm-level optimization using pre-defined demand scenarios, integrated validation of externally submitted demand, user- and operator-facing interfaces, and operational analytics remains limited. This study proposes an LLM-assisted real-time DRT operation framework comprising Service User, System Manager, and Real-time DRT Simulator layers. The Service User layer uses function calling to transform unstructured trip requests into structured dispatch parameters. The System Manager combines function-calling-based quantitative analysis with retrieval-augmented generation to support natural-language access to operational data and domain knowledge. Based on Discrete Event System Specification, the simulator processes externally submitted and simulation-generated demands within a unified event structure under common dispatching and routing logic. Three experiments were conducted. Experiments 1 and 2 functionally evaluated the rider request-processing interface and the function-calling-based quantitative-query path of the System Manager, yielding average response latencies of 1.22 and 2.21 s, respectively. Experiment 3 independently evaluated the simulator through a system-level stress test using context-based synchronized demand. Across all scenarios, synchronized demand increased waiting times for the target passenger group. Although this group represented approximately 20% of successfully served passengers, it accounted for 26.5–28.5% of total waiting time. The effect appeared largely localized and was partially obscured in aggregate metrics because background-passenger performance was stable. These results demonstrate the functional feasibility of the LLM-assisted interfaces under the prototype conditions and show that synchronized-demand stress testing can reveal localized delay burdens that aggregate evaluations may overlook.
Related
- Cognitive Warfare, Hybrid Pressure, and Sovereign Resilience: An Operations Research Framework Applied to the Iranian Case (2017--2026)
- Integrating Data Center Flexibility into Power System Operations: A Framework for Temporal Redispatch
- A novel machine learning-based framework for integrating scheduling and control in continuous multiproduct chemical process operations
- Monotonicity of the Rényi channel capacity under non-signaling assisted channel simulation
- Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference
BibTeX
@article{kim2026llmassisted,
title = {{An LLM-assisted real-time simulation framework for demand-responsive transport operations}},
author = {Jun-Woo Kim and Min-Ho Choi and Sun-Woo Lee and Kyung-Min Seo},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0360420},
url = {https://doi.org/10.1371/journal.pone.0360420},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - An LLM-assisted real-time simulation framework for demand-responsive transport operations
AU - Jun-Woo Kim
AU - Min-Ho Choi
AU - Sun-Woo Lee
AU - Kyung-Min Seo
PY - 2026
DA - 2026/10/27
JO - PLOS One
DO - 10.1371/journal.pone.0360420
UR - https://doi.org/10.1371/journal.pone.0360420
AB - Demand-responsive transport (DRT) is a dynamic service whose performance depends not only on dispatching and routing algorithms but also on how externally submitted demand is captured, interpreted, and incorporated into operations. Although prior studies have largely emphasized algorithm-level optimization using pre-defined demand scenarios, integrated validation of externally submitted demand, user- and operator-facing interfaces, and operational analytics remains limited. This study proposes an LLM-assisted real-time DRT operation framework comprising Service User, System Manager, and Real-time DRT Simulator layers. The Service User layer uses function calling to transform unstructured trip requests into structured dispatch parameters. The System Manager combines function-calling-based quantitative analysis with retrieval-augmented generation to support natural-language access to operational data and domain knowledge. Based on Discrete Event System Specification, the simulator processes externally submitted and simulation-generated demands within a unified event structure under common dispatching and routing logic. Three experiments were conducted. Experiments 1 and 2 functionally evaluated the rider request-processing interface and the function-calling-based quantitative-query path of the System Manager, yielding average response latencies of 1.22 and 2.21 s, respectively. Experiment 3 independently evaluated the simulator through a system-level stress test using context-based synchronized demand. Across all scenarios, synchronized demand increased waiting times for the target passenger group. Although this group represented approximately 20% of successfully served passengers, it accounted for 26.5–28.5% of total waiting time. The effect appeared largely localized and was partially obscured in aggregate metrics because background-passenger performance was stable. These results demonstrate the functional feasibility of the LLM-assisted interfaces under the prototype conditions and show that synchronized-demand stress testing can reveal localized delay burdens that aggregate evaluations may overlook.
SN - 1932-6203
ER -