An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems

• URL: http://arxiv.org/abs/2510.16701v1
• Date: Sun, 19 Oct 2025 03:59:25 GMT
• Title: An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
• Authors: Ni Zhang, Zhiguang Cao, Jianan Zhou, Cong Zhang, Yew-Soon Ong,
• Abstract summary: We propose an Agentic Framework with LLMs (AFL) for solving complex vehicle routing problems.<n>AFL directly extracts knowledge from raw inputs and enables self-contained code generation.<n>We show that AFL substantially outperforms existing LLM-based baselines in both code reliability and solution feasibility.
• Score: 66.60904891478687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks [62.031889234230725]
  6G networks rely on complex cross-layer optimization.<n> manually translating high-level intents into mathematical formulations remains a bottleneck.<n>We present ComAgent, a multi-LLM agentic AI framework.
  arXiv  Detail & Related papers  (2026-01-27T13:43:59Z)
• Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control [11.796330722859574]
  We show that employing LLMs as end-to-end solvers incurs a significant "hallucination tax"<n>We propose a hybrid agentic framework that strictly decouples semantic reasoning from mathematical calculation.<n>Our results position LLMs as natural-language interfaces that make rigorous, solver-based policies accessible to non-experts.
  arXiv  Detail & Related papers  (2025-12-31T21:45:54Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• Large Language Models as End-to-end Combinatorial Optimization Solvers [45.32050615257007]
  Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms.<n>Existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility.<n>This paper introduces a novel framework that empowers large language models (LLMs) to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions.
  arXiv  Detail & Related papers  (2025-09-21T01:30:30Z)
• A Large Language Model-Enhanced Q-learning for Capacitated Vehicle Routing Problem with Time Windows [3.0518581575184225]
  This paper proposes a novel Q-learning framework to address the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW)<n>Our framework achieves a 7.3% average reduction in cost compared to traditional Q-learning, with fewer training steps required for convergence.
  arXiv  Detail & Related papers  (2025-05-09T16:45:43Z)
• ARS: Automatic Routing Solver with Large Language Models [19.975885289738688]
  This paper introduces RoutBench, a benchmark of 1,000 VRP variants derived from 24 attributes, for evaluating the effectiveness of automatic routing solvers.<n>Along with RoutBench, we present the Automatic Routing Solver (ARS), which employs Large Language Model (LLM) agents to enhance a backbone algorithm framework.<n>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.
  arXiv  Detail & Related papers  (2025-02-21T10:14:55Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning [12.80689911863731]
  Sibyl is a powerful framework designed to tackle complex reasoning tasks by efficiently leveraging a minimal set of tools. Sibyl implements a multi-agent debate-based jury to self-refine the final answers, ensuring a comprehensive and balanced approach. Our experimental results on the GAIA benchmark test set reveal that the Sibyl agent achieves state-of-the-art performance with an average score of 34.55%.
  arXiv  Detail & Related papers  (2024-07-15T13:45:40Z)
• LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving [84.31119464141631]
  This work employs Large Language Models (LLMs) as a decision-making component for complex autonomous driving scenarios.<n>Extensive experiments demonstrate that our proposed method not only consistently surpasses baseline approaches in single-vehicle tasks, but also helps handle complex driving behaviors even multi-vehicle coordination.
  arXiv  Detail & Related papers  (2023-10-04T17:59:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.