Warehouse Spatial Question Answering with LLM Agent
This work addresses spatial question answering for warehouse management, representing an incremental improvement over previous methods by focusing on data efficiency.
The paper tackles the challenge of spatial understanding in complex indoor warehouse scenarios by proposing an LLM agent system with advanced spatial reasoning, achieving high accuracy and efficiency in tasks like object retrieval, counting, and distance estimation on the 2025 AI City Challenge dataset.
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 on the 2025 AI City Challenge Physical AI Spatial Intelligence Warehouse dataset demonstrate that our system achieves high accuracy and efficiency in tasks such as object retrieval, counting, and distance estimation. The code is available at: https://github.com/hsiangwei0903/SpatialAgent