LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
Abstract
While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We propose a novel framework where a large language model (LLM) agent iteratively proposes hub capacity decisions guided by natural-language business context descriptions. The key mechanism is a chain-of-thought reasoning protocol: the LLM constructs a structured decision table that maps each contextual item to specific capacity adjustments based on the implied direction and magnitude of changes. The new capacity decision is then validated through a feedback loop with an optimization model, which provides routing-based performance metrics to guide the agent's selection. On a real-world 13-hub freight network in the southeastern US, our framework achieves a 2.8% optimality gap relative to the hidden ground-truth, a significant improvement over the 11.0% gap produced by the traditional optimization model without textual business inputs. This demonstrates that LLMs can serve as a contextual bridge, integrating qualitative business insights into Operations Research workflows.
Related
- Protect the Decision, Not the Disaster: Regret-Robust Capacity Sizing and Positioning with Transportation Recourse
- Time to AC-t: When AC-transmission changes capacity expansion planning
- Multiobjective Γ-Robust Port Service-Capacity Planning Under Demand Uncertainty: Evidence from Chilean Vessel Movements
- Do Machine Learning-Guided Proactive Full Capacity Protocols Mitigate Emergency Department Overcrowding? A Simulation-Based Evaluation
- SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation
BibTeX
@misc{liu2026llmguided,
title = {{LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs}},
author = {Xiaoyue Liu and Zheng Dong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.03651},
eprint = {2607.03651},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.03651},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
AU - Xiaoyue Liu
AU - Zheng Dong
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2607.03651
UR - https://arxiv.org/abs/2607.03651
AB - While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We propose a novel framework where a large language model (LLM) agent iteratively proposes hub capacity decisions guided by natural-language business context descriptions. The key mechanism is a chain-of-thought reasoning protocol: the LLM constructs a structured decision table that maps each contextual item to specific capacity adjustments based on the implied direction and magnitude of changes. The new capacity decision is then validated through a feedback loop with an optimization model, which provides routing-based performance metrics to guide the agent's selection. On a real-world 13-hub freight network in the southeastern US, our framework achieves a 2.8% optimality gap relative to the hidden ground-truth, a significant improvement over the 11.0% gap produced by the traditional optimization model without textual business inputs. This demonstrates that LLMs can serve as a contextual bridge, integrating qualitative business insights into Operations Research workflows.
ER -