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

arXiv: https://arxiv.org/abs/2508.17971 · HTML: https://mlsanity.com/paper/2508.17971/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 10 of 10)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents](https://mlsanity.com/paper/2403.03101/) (2024)
- [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://mlsanity.com/paper/2404.11943/) (2024)
- [Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet](https://mlsanity.com/paper/2401.03630/) (2024)
- [Transformers meet Neural Algorithmic Reasoners](https://mlsanity.com/paper/2406.09308/) (2024)
- [Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling](https://mlsanity.com/paper/2412.15305/) (2024)
- [A Generalization of Convolutional Neural Networks to Graph-Structured Data](https://mlsanity.com/paper/1704.08165/) (2017)
- [ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs](https://mlsanity.com/paper/2502.13162/) (2025)

## Built on by (most cited first, 1 of 1)

- [Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.11824/) (2025)

## Abstract (arXiv)

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.