# How Well Do Multimodal Models Reason on ECG Signals?

arXiv: https://arxiv.org/abs/2603.00312 · HTML: https://mlsanity.com/paper/2603.00312/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://mlsanity.com/paper/2412.03104/) (2024)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2305.16582/) (2023)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images](https://mlsanity.com/paper/2503.06073/) (2025)
- [OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data](https://mlsanity.com/paper/2510.02410/) (2025)
- [The Anatomy of a Personal Health Agent](https://mlsanity.com/paper/2508.20148/) (2025)
- [MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning](https://mlsanity.com/paper/2406.06620/) (2024)
- [Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting](https://mlsanity.com/paper/2502.07608/) (2025)

## Built on by (most cited first, 3 of 3)

- [TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series](https://mlsanity.com/paper/2608.03391/) (2026)
- [Lapras: Latent Reasoning for Time Series Language Models](https://mlsanity.com/paper/2610.11111/) (2026)
- [ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution](https://mlsanity.com/paper/2610.17718/) (2026)

## Abstract (arXiv)

While multimodal large language models offer a promising solution to the "black box" nature of health AI by generating interpretable reasoning traces, verifying the validity of these traces remains a critical challenge. Existing evaluation methods are either unscalable, relying on manual clinician review, or superficial, utilizing proxy metrics (e.g. QA) that fail to capture the semantic correctness of clinical logic. In this work, we introduce a reproducible framework for evaluating reasoning in ECG signals. We propose decomposing reasoning into two distinct, components: (i) Perception, the accurate identification of patterns within the raw signal, and (ii) Deduction, the logical application of domain knowledge to those patterns. To evaluate Perception, we employ an agentic framework that generates code to empirically verify the temporal structures described in the reasoning trace. To evaluate Deduction, we measure the alignment of the model's logic against a structured database of established clinical criteria in a retrieval-based approach. This dual-verification method enables the scalable assessment of "true" reasoning capabilities.