Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Kechen, Tao, Yaotian, Wen, Ximing, Sun, Quanwei, Gong, Zifei, Xu, Chang, Zhang, Xizhe, Ji, Tianbo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.24306
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911103235129344
author Li, Kechen
Tao, Yaotian
Wen, Ximing
Sun, Quanwei
Gong, Zifei
Xu, Chang
Zhang, Xizhe
Ji, Tianbo
author_facet Li, Kechen
Tao, Yaotian
Wen, Ximing
Sun, Quanwei
Gong, Zifei
Xu, Chang
Zhang, Xizhe
Ji, Tianbo
contents Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional algorithms' guidance into prompting. Our benchmark evaluates six LLMs ranging from 7B to 72B parameters across various map sizes, assessing their performance in correctness, optimality, and efficiency in grid environments with varying sizes. Our results show that AoT significantly boosts performance across all model sizes, particularly in larger or more complex environments, suggesting a promising approach to addressing path planning challenges. Our code is open-sourced at https://github.com/LinChance/GridRoute.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments
Li, Kechen
Tao, Yaotian
Wen, Ximing
Sun, Quanwei
Gong, Zifei
Xu, Chang
Zhang, Xizhe
Ji, Tianbo
Artificial Intelligence
Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional algorithms' guidance into prompting. Our benchmark evaluates six LLMs ranging from 7B to 72B parameters across various map sizes, assessing their performance in correctness, optimality, and efficiency in grid environments with varying sizes. Our results show that AoT significantly boosts performance across all model sizes, particularly in larger or more complex environments, suggesting a promising approach to addressing path planning challenges. Our code is open-sourced at https://github.com/LinChance/GridRoute.
title GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments
topic Artificial Intelligence
url https://arxiv.org/abs/2505.24306