mlsanityData to 14 Oct 2026

Warehouse Spatial Question Answering with LLM Agent

arXiv 2507.10778 ↗First posted 14 Jul 2025cs.CV cs.AIcited by 3

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

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

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 22 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

15 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making9 Oct
  2. 2024Agent3D-Zero: An Agent for Zero-shot 3D Understanding18 Mar
  3. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agent15 Mar
  4. 2023LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent21 Sep

Other references · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  3. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  4. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
  5. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 152
  6. 2024Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understandingcited by 138
  7. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 67
  8. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  9. 2024VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Groundingcited by 56
  10. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  11. 2025ToSA: Token Merging with Spatial Awarenesscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025The 9th AI City Challengecited by 12
  2. 2026UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluationscited by 1
  3. 2026Memory Tree Guided Key Frame Querying for Efficient 3D Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph-Enhanced Large Language Models for Spatial Search
  2. 2025A Survey of Large Language Model Agents for Question Answering
  3. 2026Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
  4. 2025CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
  5. 2025Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning
  6. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering
  7. 2025SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence
  8. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models