@inproceedings{wasi-etal-2026-spatial,
title = "Spatial Reasoning in Multimodal Foundation Models: A Survey of Spatial Understanding in {LLM}s and {VLM}s",
author = "Wasi, Azmine Toushik and
Rahman, Md. Masudur and
Rahman, Abdur and
Topu, Mohsin Mahmud and
Ali, Mohammed Eunus and
Islam, Riashat and
Parvez, Md Rizwan",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.67/",
pages = "1451--1479",
ISBN = "979-8-89176-439-2",
abstract = "Spatial reasoning, the ability to represent and reason about spatial relations, geometry, topology, and embodied environments, is increasingly vital for evaluating and deploying large language models (LLMs) and vision{--}language models (VLMs). While multimodal foundation models show strong performance on spatial benchmarks, navigation, and embodied planning, much of this stems from shallow pattern matching rather than grounded spatial understanding. This review offers a comprehensive, framework-driven analysis of spatial reasoning in LLMs and VLMs, covering tasks, representations, datasets, benchmarks, architectures, training, and failure modes. We also link spatial reasoning to embodied AI, emphasizing challenges in generalization, compositionality, and grounding. Our survey unifies diverse fields, NLP, vision, robotics, and cognitive science, to guide the development of truly spatially grounded foundation models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wasi-etal-2026-spatial">
<titleInfo>
<title>Spatial Reasoning in Multimodal Foundation Models: A Survey of Spatial Understanding in LLMs and VLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Masudur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohsin</namePart>
<namePart type="given">Mahmud</namePart>
<namePart type="family">Topu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Eunus</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riashat</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Spatial reasoning, the ability to represent and reason about spatial relations, geometry, topology, and embodied environments, is increasingly vital for evaluating and deploying large language models (LLMs) and vision–language models (VLMs). While multimodal foundation models show strong performance on spatial benchmarks, navigation, and embodied planning, much of this stems from shallow pattern matching rather than grounded spatial understanding. This review offers a comprehensive, framework-driven analysis of spatial reasoning in LLMs and VLMs, covering tasks, representations, datasets, benchmarks, architectures, training, and failure modes. We also link spatial reasoning to embodied AI, emphasizing challenges in generalization, compositionality, and grounding. Our survey unifies diverse fields, NLP, vision, robotics, and cognitive science, to guide the development of truly spatially grounded foundation models.</abstract>
<identifier type="citekey">wasi-etal-2026-spatial</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.67/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1451</start>
<end>1479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spatial Reasoning in Multimodal Foundation Models: A Survey of Spatial Understanding in LLMs and VLMs
%A Wasi, Azmine Toushik
%A Rahman, Md. Masudur
%A Rahman, Abdur
%A Topu, Mohsin Mahmud
%A Ali, Mohammed Eunus
%A Islam, Riashat
%A Parvez, Md Rizwan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F wasi-etal-2026-spatial
%X Spatial reasoning, the ability to represent and reason about spatial relations, geometry, topology, and embodied environments, is increasingly vital for evaluating and deploying large language models (LLMs) and vision–language models (VLMs). While multimodal foundation models show strong performance on spatial benchmarks, navigation, and embodied planning, much of this stems from shallow pattern matching rather than grounded spatial understanding. This review offers a comprehensive, framework-driven analysis of spatial reasoning in LLMs and VLMs, covering tasks, representations, datasets, benchmarks, architectures, training, and failure modes. We also link spatial reasoning to embodied AI, emphasizing challenges in generalization, compositionality, and grounding. Our survey unifies diverse fields, NLP, vision, robotics, and cognitive science, to guide the development of truly spatially grounded foundation models.
%U https://aclanthology.org/2026.aacl-long.67/
%P 1451-1479
Markdown (Informal)
[Spatial Reasoning in Multimodal Foundation Models: A Survey of Spatial Understanding in LLMs and VLMs](https://aclanthology.org/2026.aacl-long.67/) (Wasi et al., AACL-IJCNLP 2026)
ACL
- Azmine Toushik Wasi, Md. Masudur Rahman, Abdur Rahman, Mohsin Mahmud Topu, Mohammed Eunus Ali, Riashat Islam, and Md Rizwan Parvez. 2026. Spatial Reasoning in Multimodal Foundation Models: A Survey of Spatial Understanding in LLMs and VLMs. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1451–1479, Hengqin, China. Association for Computational Linguistics.