# HEARTS: Benchmarking LLM Reasoning on Health Time Series

arXiv: https://arxiv.org/abs/2603.06638 · HTML: https://mlsanity.com/paper/2603.06638/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 31 of its 95 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 31)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [Coswara -- A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis](https://mlsanity.com/paper/2005.10548/) (2020)
- [MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering](https://mlsanity.com/paper/2503.16858/) (2025)
- [TimeSeriesExam: A time series understanding exam](https://mlsanity.com/paper/2410.14752/) (2024)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [Can LLMs Understand Time Series Anomalies?](https://mlsanity.com/paper/2410.05440/) (2024)
- [OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data](https://mlsanity.com/paper/2510.02410/) (2025)
- [TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models](https://mlsanity.com/paper/2509.24803/) (2025)
- [In-context Time Series Predictor](https://mlsanity.com/paper/2405.14982/) (2024)
- [When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference](https://mlsanity.com/paper/2509.01822/) (2025)
- [BEDTime: A Unified Benchmark for Automatically Describing Time Series](https://mlsanity.com/paper/2509.05215/) (2025)
- [TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering](https://mlsanity.com/paper/2510.07432/) (2025)
- [An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation](https://mlsanity.com/paper/2502.12836/) (2025)
- [Human Activity Recognition Using Self-Supervised Representations of Wearable Data](https://mlsanity.com/paper/2304.14912/) (2023)
- [Cough Classification using Few-Shot Learning](https://mlsanity.com/paper/2509.09515/) (2025)

## Built on by (most cited first, 11 of 11)

- [SleepLM: Natural-Language Intelligence for Human Sleep](https://mlsanity.com/paper/2602.23605/) (2026)
- [OSF: On Pre-training and Scaling of Sleep Foundation Models](https://mlsanity.com/paper/2603.00190/) (2026)
- [GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring](https://mlsanity.com/paper/2605.30865/) (2026)
- [Inertia-1: An Open Exploration of Wearable Motion Foundation Models](https://mlsanity.com/paper/2607.06617/) (2026)
- [TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health](https://mlsanity.com/paper/2605.21295/) (2026)
- [Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series](https://mlsanity.com/paper/2607.04245/) (2026)
- [An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data](https://mlsanity.com/paper/2604.14615/) (2026)
- [BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding](https://mlsanity.com/paper/2608.04156/) (2026)
- [TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models](https://mlsanity.com/paper/2609.13457/) (2026)
- [TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models](https://mlsanity.com/paper/2610.04407/) (2026)
- [Sensor-Language-Action Models](https://mlsanity.com/paper/2610.08244/) (2026)

## Abstract (arXiv)

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.