@inproceedings{kaesberg-etal-2025-sparc,
title = "{SP}a{RC}: A Spatial Pathfinding Reasoning Challenge",
author = "Kaesberg, Lars Benedikt and
Wahle, Jan Philip and
Ruas, Terry and
Gipp, Bela",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.526/",
doi = "10.18653/v1/2025.emnlp-main.526",
pages = "10359--10390",
ISBN = "979-8-89176-332-6",
abstract = "Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pathfinding Reasoning Challenge), a dataset of 1,000 2D grid pathfinding puzzles to evaluate spatial and rule-based reasoning, requiring step-by-step planning with arithmetic and geometric rules. Humans achieve near-perfect accuracy (98.0{\%}; 94.5{\%} on hard puzzles), while the best reasoning models, such as o4-mini, struggle (15.8{\%}; 1.1{\%} on hard puzzles). Models often generate invalid paths ({\ensuremath{>}}50{\%} of puzzles for o4-mini), and reasoning tokens reveal they make errors in navigation and spatial logic. Unlike humans, who take longer on hard puzzles, models fail to scale test-time compute with difficulty. Allowing models to make multiple solution attempts improves accuracy, suggesting potential for better spatial reasoning with improved training and efficient test-time scaling methods. SPaRC can be used as a window into models' spatial reasoning limitations and drive research toward new methods that excel in abstract, multi-step problem-solving."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaesberg-etal-2025-sparc">
<titleInfo>
<title>SPaRC: A Spatial Pathfinding Reasoning Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="given">Benedikt</namePart>
<namePart type="family">Kaesberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Philip</namePart>
<namePart type="family">Wahle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Ruas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pathfinding Reasoning Challenge), a dataset of 1,000 2D grid pathfinding puzzles to evaluate spatial and rule-based reasoning, requiring step-by-step planning with arithmetic and geometric rules. Humans achieve near-perfect accuracy (98.0%; 94.5% on hard puzzles), while the best reasoning models, such as o4-mini, struggle (15.8%; 1.1% on hard puzzles). Models often generate invalid paths (\ensuremath>50% of puzzles for o4-mini), and reasoning tokens reveal they make errors in navigation and spatial logic. Unlike humans, who take longer on hard puzzles, models fail to scale test-time compute with difficulty. Allowing models to make multiple solution attempts improves accuracy, suggesting potential for better spatial reasoning with improved training and efficient test-time scaling methods. SPaRC can be used as a window into models’ spatial reasoning limitations and drive research toward new methods that excel in abstract, multi-step problem-solving.</abstract>
<identifier type="citekey">kaesberg-etal-2025-sparc</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.526</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.526/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>10359</start>
<end>10390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPaRC: A Spatial Pathfinding Reasoning Challenge
%A Kaesberg, Lars Benedikt
%A Wahle, Jan Philip
%A Ruas, Terry
%A Gipp, Bela
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F kaesberg-etal-2025-sparc
%X Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pathfinding Reasoning Challenge), a dataset of 1,000 2D grid pathfinding puzzles to evaluate spatial and rule-based reasoning, requiring step-by-step planning with arithmetic and geometric rules. Humans achieve near-perfect accuracy (98.0%; 94.5% on hard puzzles), while the best reasoning models, such as o4-mini, struggle (15.8%; 1.1% on hard puzzles). Models often generate invalid paths (\ensuremath>50% of puzzles for o4-mini), and reasoning tokens reveal they make errors in navigation and spatial logic. Unlike humans, who take longer on hard puzzles, models fail to scale test-time compute with difficulty. Allowing models to make multiple solution attempts improves accuracy, suggesting potential for better spatial reasoning with improved training and efficient test-time scaling methods. SPaRC can be used as a window into models’ spatial reasoning limitations and drive research toward new methods that excel in abstract, multi-step problem-solving.
%R 10.18653/v1/2025.emnlp-main.526
%U https://aclanthology.org/2025.emnlp-main.526/
%U https://doi.org/10.18653/v1/2025.emnlp-main.526
%P 10359-10390
Markdown (Informal)
[SPaRC: A Spatial Pathfinding Reasoning Challenge](https://aclanthology.org/2025.emnlp-main.526/) (Kaesberg et al., EMNLP 2025)
ACL
- Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 2025. SPaRC: A Spatial Pathfinding Reasoning Challenge. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 10359–10390, Suzhou, China. Association for Computational Linguistics.