# LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs

arXiv: https://arxiv.org/abs/2607.03651 · HTML: https://mlsanity.com/paper/2607.03651/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [OptiMUS: Optimization Modeling Using MIP Solvers and large language models](https://mlsanity.com/paper/2310.06116/) (2023)
- [DeLLMa: Decision Making Under Uncertainty with Large Language Models](https://mlsanity.com/paper/2402.02392/) (2024)
- [Neural Spectral Marked Point Processes](https://mlsanity.com/paper/2106.10773/) (2021)
- [Spatio-temporal point processes with deep non-stationary kernels](https://mlsanity.com/paper/2211.11179/) (2022)
- [Conditional Generative Modeling for High-dimensional Marked Temporal Point Processes](https://mlsanity.com/paper/2305.12569/) (2023)
- [Deep graph kernel point processes over networks](https://mlsanity.com/paper/2306.11313/) (2023)
- [The Potential of Large Language Models in Supply Chain Management: Advancing Decision-Making, Efficiency, and Innovation](https://mlsanity.com/paper/2501.15411/) (2025)
- [Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study](https://mlsanity.com/paper/2508.21622/) (2025)
- [Stochastic Service Network Design with Different Operational Patterns for Hyperconnected Relay Transportation](https://mlsanity.com/paper/2402.06222/) (2024)
- [LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection](https://mlsanity.com/paper/2510.25799/) (2025)
- [Logistics Hub Capacity Deployment in Hyperconnected Transportation Network Under Uncertainty](https://mlsanity.com/paper/2402.06227/) (2024)
- [Multi-Period Stochastic Logistic Hub Capacity Planning for Relay Transportation](https://mlsanity.com/paper/2406.16010/) (2024)
- [GreenTEA: Gradient Descent with Topic-modeling and Evolutionary Auto-prompting](https://mlsanity.com/paper/2508.16603/) (2025)
- [Dynamic Containerized Modular Capacity Planning and Resource Allocation in Hyperconnected Supply Chain Ecosystems](https://mlsanity.com/paper/2511.07845/) (2025)
- [SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making](https://mlsanity.com/paper/2511.15202/) (2025)
- [Modular and Mobile Capacity Planning for Hyperconnected Supply Chain Networks](https://mlsanity.com/paper/2601.11107/) (2026)
- [Two-Echelon Delivery Vehicle Sharing and Repositioning in Hyperconnected Urban Logistic Networks](https://mlsanity.com/paper/2606.17608/) (2026)

## Abstract (arXiv)

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.