{"ID":2878553,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17971","arxiv_id":"2508.17971","title":"Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding","abstract":"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.","short_abstract":"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 pr...","url_abs":"https://arxiv.org/abs/2508.17971","url_pdf":"https://arxiv.org/pdf/2508.17971v1","authors":"[\"Pu Feng\",\"Size Wang\",\"Yuhong Cao\",\"Junkang Liang\",\"Rongye Shi\",\"Wenjun Wu\"]","published":"2025-08-25T12:38:08Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.RO\"]","methods":"[\"Graph Neural Network\",\"Large Language Model\",\"Language Model\"]","has_code":false}