ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms.

arXiv:2609.33117v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning. Real cardiac monitoring is different. A