Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Pu, Wang, Size, Cao, Yuhong, Liang, Junkang, Shi, Rongye, Wu, Wenjun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915462020857856
author Feng, Pu
Wang, Size
Cao, Yuhong
Liang, Junkang
Shi, Rongye
Wu, Wenjun
author_facet Feng, Pu
Wang, Size
Cao, Yuhong
Liang, Junkang
Shi, Rongye
Wu, Wenjun
contents The development and application of large language models (LLM) have demonstrated that foundational models can be utilized to solve a wide array of tasks. However, their performance in multi-agent path finding (MAPF) tasks has been less than satisfactory, with only a few studies exploring this area. MAPF is a complex problem requiring both planning and multi-agent coordination. To improve the performance of LLM in MAPF tasks, we propose a novel framework, LLM-NAR, which leverages neural algorithmic reasoners (NAR) to inform LLM for MAPF. LLM-NAR consists of three key components: an LLM for MAPF, a pre-trained graph neural network-based NAR, and a cross-attention mechanism. This is the first work to propose using a neural algorithmic reasoner to integrate GNNs with the map information for MAPF, thereby guiding LLM to achieve superior performance. LLM-NAR can be easily adapted to various LLM models. Both simulation and real-world experiments demonstrate that our method significantly outperforms existing LLM-based approaches in solving MAPF problems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17971
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding
Feng, Pu
Wang, Size
Cao, Yuhong
Liang, Junkang
Shi, Rongye
Wu, Wenjun
Artificial Intelligence
Robotics
The development and application of large language models (LLM) have demonstrated that foundational models can be utilized to solve a wide array of tasks. However, their performance in multi-agent path finding (MAPF) tasks has been less than satisfactory, with only a few studies exploring this area. MAPF is a complex problem requiring both planning and multi-agent coordination. To improve the performance of LLM in MAPF tasks, we propose a novel framework, LLM-NAR, which leverages neural algorithmic reasoners (NAR) to inform LLM for MAPF. LLM-NAR consists of three key components: an LLM for MAPF, a pre-trained graph neural network-based NAR, and a cross-attention mechanism. This is the first work to propose using a neural algorithmic reasoner to integrate GNNs with the map information for MAPF, thereby guiding LLM to achieve superior performance. LLM-NAR can be easily adapted to various LLM models. Both simulation and real-world experiments demonstrate that our method significantly outperforms existing LLM-based approaches in solving MAPF problems.
title Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2508.17971