arXiv：cs.LG（机器学习，全量分类）· Xiaoyue Liu, Zheng Dong·· 15 小时前AI 评分33
LLM 智能体如何用文本业务输入优化交通枢纽容量规划
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
AI 导读
研究者提出一种 LLM 智能体框架，通过链式推理协议将自然语言业务背景映射为结构化决策表，再经优化模型反馈回路验证枢纽容量决策。在美国东南部一个真实的 13 枢纽货运网络上，该框架相对隐藏真值的最优性差距为 2.8%，而传统优化模型在无文本业务输入时为 11.0%。
正文
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.
| Subjects: | Machine Learning (cs.LG); Optimization and Control (math.OC) |
| Cite as: | arXiv:2607.03651 [cs.LG] |
| (or arXiv:2607.03651v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03651 arXiv-issued DOI via DataCite |
Submission history
From: Zheng Dong [view email]
[v1]
Sat, 4 Jul 2026 00:26:19 UTC (246 KB)
[v2]
Fri, 17 Jul 2026 08:58:34 UTC (246 KB)
[v3]
Thu, 1 Oct 2026 07:18:13 UTC (224 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org