用大模型理解业务描述，自动优化物流枢纽容量。
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
- 大模型通过思维链分析文本描述，生成容量调整建议。
- 在真实13枢纽网络中，优化差距仅2.8%，优于传统模型的11.0%。
- 适合需要融合业务经验的物流与运筹决策场景。
传统枢纽容量规划模型虽能高效处理定量输入，却难以解析定性业务背景。本文提出一种新框架：基于大语言模型（LLM）代理，通过自然语言业务描述迭代生成容量决策。核心机制是思维链推理协议——LLM构建结构化决策表，将每项业务上下文映射为具体容量调整方向与幅度。新决策经由优化模型反馈验证，后者提供基于路径的性能指标以指导代理选择。在美东南部真实13枢纽货运网络上，该框架相对于隐藏的真实最优解，仅产生2.8%的最优性差距，显著优于无文本输入的传统优化模型所达的11.0%差距。结果表明，大模型可作为上下文桥梁，实现定性业务洞察与运筹学流程的有效融合。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。