[2505.24069] Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures

-->

Computer Science > Machine Learning

arXiv:2505.24069 (cs)

[Submitted on 29 May 2025 (v1), last revised 30 May 2026 (this version, v4)]

Title:Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures

Authors:Yu He, Yingxi Li, Colin White, Ellen Vitercik<br>View a PDF of the paper titled Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures, by Yu He and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Large language models (LLMs) are deployed on increasingly complex tasks that require multi-step decision-making. Understanding their algorithmic reasoning abilities is therefore crucial. However, we lack a diagnostic benchmark for evaluating these capabilities. We propose to use data structures as a principled lens: as fundamental building blocks of algorithms, they naturally probe structural reasoning - the ability to understand and manipulate relationships such as order, hierarchy, and connectivity that underpin algorithmic reasoning. We introduce DSR-Bench (Data Structure Reasoning Benchmark), spanning 20 data structures, 35 operations, and 4,140 problem instances. DSR-Bench features hierarchical task organization, fully automated generation and evaluation, and fine-grained diagnostics. Evaluating 13 state-of-the-art LLMs reveals critical limitations: the top-performing model achieves only 0.46/1 on challenging instances. Three auxiliary probes targeting more realistic usages expose further weaknesses: models perform poorly on spatial data and context-rich scenarios, and they struggle to reason over their own code.

Comments:<br>Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2505.24069 [cs.LG]

(or<br>arXiv:2505.24069v4 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2505.24069

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yu He [view email]<br>[v1]<br>Thu, 29 May 2025 23:24:53 UTC (520 KB)

[v2]<br>Tue, 14 Oct 2025 01:24:23 UTC (598 KB)

[v3]<br>Tue, 10 Feb 2026 22:32:27 UTC (964 KB)

[v4]<br>Sat, 30 May 2026 00:02:27 UTC (1,026 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures, by Yu He and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2025-05

Change to browse by:

cs<br>cs.AI

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)