Preprint · 2026 · Open access
HEARTS: Benchmarking LLM Reasoning on Health Time Series
arXiv (Cornell University) · Published 25 February 2026 · DOI 10.48550/arxiv.2603.06638
In brief
“HEARTS: Benchmarking LLM Reasoning on Health Time Series” is a 2026 preprint by Sirui Li and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 14 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 14
- Most cited in
- 2026 (14)
- References
- 78
- Authors
- 7
Abstract
The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to general-purpose reasoning. Yet, existing benchmarks cover only a small set of health time series modalities and tasks, failing to reflect the diverse domains and extensive temporal dependencies inherent in real-world physiological modeling. To bridge these gaps, we introduce HEARTS (Health Reasoning over Time Series), a unified benchmark for evaluating hierarchical reasoning capabilities of LLMs over general health time series. HEARTS integrates 16 real-world datasets across 12 health domains and 20 signal modalities, and defines a comprehensive taxonomy of 110 tasks grouped into four core capabilities: Perception, Inference, Generation, and Deduction. Evaluating 16 state-of-the-art LLMs on more than 20K test samples reveals intriguing findings. First, LLMs substantially underperform specialized models, and their performance is only weakly related to general reasoning scores. Moreover, LLMs often rely on simple heuristics and struggle with multi-step temporal reasoning. Finally, performance declines with increasing temporal complexity, with similar failure modes within model families, indicating that scaling alone is insufficient. By making these gaps measurable, HEARTS provides a standardized testbed and living benchmark for developing next-generation LLM agents capable of reasoning over diverse health signals.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, S., Xiao, S., Joshi, M., Metwally, A. A., McDuff, D., Wang, W. W., & Yang, Y. (2026). HEARTS: Benchmarking LLM Reasoning on Health Time Series. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06638
MLA 9
Li, Sirui, et al. “HEARTS: Benchmarking LLM Reasoning on Health Time Series.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.06638.
Chicago
Li, Sirui, Shuhan Xiao, Mihir Joshi, Ahmed A. Metwally, Daniel McDuff, Wei William Wang, and Yuzhe Yang. 2026. “HEARTS: Benchmarking LLM Reasoning on Health Time Series.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06638.
Harvard
Li, S. et al. (2026) ‘HEARTS: Benchmarking LLM Reasoning on Health Time Series’, arXiv (Cornell University). doi:10.48550/arxiv.2603.06638.
IEEE
S. Li et al., “HEARTS: Benchmarking LLM Reasoning on Health Time Series,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.06638.
BibTeX
@misc{li2026hearts,
title = {{HEARTS: Benchmarking LLM Reasoning on Health Time Series}},
author = {Li, Sirui and Xiao, Shuhan and Joshi, Mihir and Metwally, Ahmed A. and McDuff, Daniel and Wang, Wei William and Yang, Yuzhe},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2603.06638},
url = {https://doi.org/10.48550/arxiv.2603.06638}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- large language models
- benchmarking
- hierarchical reasoning
- temporal reasoning
- physiological signals
- health data
- LLM agents
- multi-step reasoning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Li, S., Xiao, S., Joshi, M., Metwally, A. A., McDuff, D., Wang, W. W., & Yang, Y. (2026). HEARTS: Benchmarking LLM Reasoning on Health Time Series. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.06638
How many times has this paper been cited?
14 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sirui Li, Shuhan Xiao, Mihir Joshi, Ahmed A. Metwally, Daniel McDuff, Wei William Wang, Yuzhe Yang.
What is the DOI of this paper?
10.48550/arxiv.2603.06638, permanently at https://doi.org/10.48550/arxiv.2603.06638. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.