用大模型自动生成带约束的路径求解代码，解决真实场景复杂路由问题。
ARS: Automatic Routing Solver with Large Language Models
- 大模型根据问题描述自动生成符合约束的启发式代码。
- 在1000种变体上解决率达91.67%，性能提升超30%。
- 适合需要快速适配复杂约束的物流与调度研发人员。
现实中的车辆路径问题（VRPs）具有多种实际约束，手动设计求解器既耗知识又费时间。尽管自动化算法设计日益受关注，现有研究仅覆盖有限的VRP变体，难以应对真实场景中复杂的普遍约束。为此，本文提出RoutBench基准，包含由24个属性生成的1000种VRP变体，用于评估自动求解器在复杂约束下的表现。同时，我们提出自动路径求解器ARS，利用大语言模型（LLM）代理，在骨干算法框架基础上，基于问题描述和数据库中选取的若干典型约束，自动生成约束感知的启发式代码。实验表明，ARS优于现有最先进LLM方法及常用求解器，在所有基准上均实现至少30%的性能提升，并能自动求解91.67%的常见VRP。
原文摘要 · Abstract (English)
Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming. Although there is increasing interest in automating the design of routing algorithms, existing research has explored only a limited array of VRP variants and fails to adequately address the complex and prevalent constraints encountered in real-world situations. To fill this gap, this paper introduces RoutBench, a benchmark of 1,000 VRP variants derived from 24 attributes, for evaluating the effectiveness of automatic routing solvers in addressing complex constraints. Along with RoutBench, we present the Automatic Routing Solver (ARS), which employs Large Language Model (LLM) agents to enhance a backbone algorithm framework by automatically generating constraint-aware heuristic code, based on problem descriptions and several representative constraints selected from a database. Our experiments show that ARS outperforms state-of-the-art LLM-based methods and commonly used solvers, automatically solving 91.67% of common VRPs and achieving at least a 30% improvement across all benchmarks.
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。