SpatialAgent: Spatial Question Answering with LLM Agent and Perception Models

Abstract

Spatial understanding has been a challenging task for existing Multi-modal Large Language Models (MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM’s spatial understanding ability. In this paper, we present a data-efficient approach. We propose a LLM agent system with strong and advanced spatial reasoning ability, which can be used to solve the challenging spatial question answering task in complex indoor warehouse scenarios. Our system integrates multiple tools that allow the LLM agent to conduct spatial reasoning and API tools interaction to answer the given complicated spatial question. Extensive evaluations demonstrate that our system achieves high accuracy and efficiency in tasks such as object retrieval, counting, and distance estimation. On the 2025 AI City Challenge Physical AI Spatial Intelligence Warehouse dataset, our system achieves 95.86% accuracy, ranking 1st place among all teams. On the SpatialBench benchmark, our system further attains 84.2% accuracy, setting a new state-of-the-art for zero-shot spatial question answering. The code is available at https://github.com/hsiangwei0903/SpatialAgent.