用大模型自动解复杂车辆路径问题，全程无需人工干预。
An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
- 构建多智能体系统，分步处理问题理解、代码生成与验证
- 在60个复杂场景中实现近100%的代码可靠性和解可行性
- 适合需要自动化求解路径规划的工业应用开发者
复杂车辆路径问题（VRPs）仍是核心挑战，需大量专家投入进行意图解析与算法设计。尽管大语言模型（LLMs）为自动化带来可能，现有方法仍依赖外部干预，限制自主性并常导致执行错误和解不可行。为此，我们提出基于大模型的智能体框架（AFL），实现从问题实例到解决方案的全流程自动化。AFL直接从原始输入提取知识，无需手工模块或外部求解器即可自动生成完整代码。为提升可信度，框架将流程分解为三个可管理子任务，并引入四个专业智能体协同工作，确保跨功能一致性与逻辑严谨性。在60个复杂VRP上（涵盖标准基准与实际变体）的实验表明，该框架在性能和泛化性上媲美精心设计的传统算法，显著优于现有基于LLM的基线，在代码可靠性与解可行性方面均达到接近100%的水平。
原文摘要 · Abstract (English)
Complex vehicle routing problems (VRPs) remain a fundamental challenge, demanding substantial expert effort for intent interpretation and algorithm design. While large language models (LLMs) offer a promising path toward automation, current approaches still rely on external intervention, which restrict autonomy and often lead to execution errors and low solution feasibility. To address these challenges, we propose an Agentic Framework with LLMs (AFL) for solving complex vehicle routing problems, achieving full automation from problem instance to solution. AFL directly extracts knowledge from raw inputs and enables self-contained code generation without handcrafted modules or external solvers. To improve trustworthiness, AFL decomposes the overall pipeline into three manageable subtasks and employs four specialized agents whose coordinated interactions enforce cross-functional consistency and logical soundness. Extensive experiments on 60 complex VRPs, ranging from standard benchmarks to practical variants, validate the effectiveness and generality of our framework, showing comparable performance against meticulously designed algorithms. Notably, it substantially outperforms existing LLM-based baselines in both code reliability and solution feasibility, achieving rates close to 100% on the evaluated 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。