Saved in:
Bibliographic Details
Main Authors: Cao, Linjiang, Wang, Maonan, Xiong, Xi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.06178
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908456553807872
author Cao, Linjiang
Wang, Maonan
Xiong, Xi
author_facet Cao, Linjiang
Wang, Maonan
Xiong, Xi
contents The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a classic NP-hard combinatorial optimization problem widely applied in logistics distribution and transportation management. Its complexity stems from the constraints of vehicle capacity and time windows, which pose significant challenges to traditional approaches. Advances in Large Language Models (LLMs) provide new possibilities for finding approximate solutions to CVRPTW. This paper proposes a novel LLM-enhanced Q-learning framework to address the CVRPTW with real-time emergency constraints. Our solution introduces an adaptive two-phase training mechanism that transitions from the LLM-guided exploration phase to the autonomous optimization phase of Q-network. To ensure reliability, we design a three-tier self-correction mechanism based on the Chain-of-Thought (CoT) for LLMs: syntactic validation, semantic verification, and physical constraint enforcement. In addition, we also prioritized replay of the experience generated by LLMs to amplify the regulatory role of LLMs in the architecture. Experimental results demonstrate that our framework achieves a 7.3\% average reduction in cost compared to traditional Q-learning, with fewer training steps required for convergence.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06178
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Large Language Model-Enhanced Q-learning for Capacitated Vehicle Routing Problem with Time Windows
Cao, Linjiang
Wang, Maonan
Xiong, Xi
Machine Learning
The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a classic NP-hard combinatorial optimization problem widely applied in logistics distribution and transportation management. Its complexity stems from the constraints of vehicle capacity and time windows, which pose significant challenges to traditional approaches. Advances in Large Language Models (LLMs) provide new possibilities for finding approximate solutions to CVRPTW. This paper proposes a novel LLM-enhanced Q-learning framework to address the CVRPTW with real-time emergency constraints. Our solution introduces an adaptive two-phase training mechanism that transitions from the LLM-guided exploration phase to the autonomous optimization phase of Q-network. To ensure reliability, we design a three-tier self-correction mechanism based on the Chain-of-Thought (CoT) for LLMs: syntactic validation, semantic verification, and physical constraint enforcement. In addition, we also prioritized replay of the experience generated by LLMs to amplify the regulatory role of LLMs in the architecture. Experimental results demonstrate that our framework achieves a 7.3\% average reduction in cost compared to traditional Q-learning, with fewer training steps required for convergence.
title A Large Language Model-Enhanced Q-learning for Capacitated Vehicle Routing Problem with Time Windows
topic Machine Learning
url https://arxiv.org/abs/2505.06178