用神经算法推理器提升大模型在多智能体路径规划中的表现
Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding
- 引入神经算法推理器与图神经网络结合地图信息
- 在仿真和真实场景中显著优于现有大模型方法
- 框架可适配多种大模型，适合路径规划研究者
大语言模型（LLM）在众多任务中展现出强大能力，但在多智能体路径规划（MAPF）任务中表现不佳，仅有少数研究涉及。MAPF需同时完成规划与多智能体协调。为提升LLM在该任务中的性能，本文提出新框架LLM-NAR，融合预训练图神经网络构建的神经算法推理器（NAR）与跨注意力机制，实现对地图信息的有效利用。这是首个将图神经网络与地图信息结合用于指导大模型进行MAPF的方案。实验表明，无论是仿真还是真实场景，该方法均显著优于现有基于大模型的方案，且可灵活适配不同大模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。