Warehouse Spatial Question Answering with LLM Agent
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915445722841088 |
|---|---|
| author | Huang, Hsiang-Wei Cheng, Jen-Hao Chen, Kuang-Ming Yang, Cheng-Yen Alattar, Bahaa Lin, Yi-Ru Kim, Pyongkun Kim, Sangwon Kim, Kwangju Huang, Chung-I Hwang, Jenq-Neng |
| author_facet | Huang, Hsiang-Wei Cheng, Jen-Hao Chen, Kuang-Ming Yang, Cheng-Yen Alattar, Bahaa Lin, Yi-Ru Kim, Pyongkun Kim, Sangwon Kim, Kwangju Huang, Chung-I Hwang, Jenq-Neng |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10778 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Warehouse Spatial Question Answering with LLM Agent Huang, Hsiang-Wei Cheng, Jen-Hao Chen, Kuang-Ming Yang, Cheng-Yen Alattar, Bahaa Lin, Yi-Ru Kim, Pyongkun Kim, Sangwon Kim, Kwangju Huang, Chung-I Hwang, Jenq-Neng Computer Vision and Pattern Recognition Artificial Intelligence 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 |
| title | Warehouse Spatial Question Answering with LLM Agent |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.10778 |