# Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers

arXiv: https://arxiv.org/abs/2607.24419 · HTML: https://mlsanity.com/paper/2607.24419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery](https://mlsanity.com/paper/2405.09783/) (2024)
- [Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram](https://mlsanity.com/paper/2402.09450/) (2024)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram](https://mlsanity.com/paper/2306.15681/) (2023)
- [Automated Hypothesis Validation with Agentic Sequential Falsifications](https://mlsanity.com/paper/2502.09858/) (2025)
- [ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback](https://mlsanity.com/paper/2402.10980/) (2024)
- [MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation](https://mlsanity.com/paper/2403.04945/) (2024)
- [From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining](https://mlsanity.com/paper/2506.21803/) (2025)
- [AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection](https://mlsanity.com/paper/2505.12594/) (2025)
- [AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning](https://mlsanity.com/paper/2602.13807/) (2026)
- [xLSTM-ECG: Multi-label ECG Classification via Feature Fusion with xLSTM](https://mlsanity.com/paper/2504.16101/) (2025)

## Abstract (arXiv)

Deep models have substantially advanced 12-lead ECG classification, yet their refinement still relies heavily on human experts to inspect failures and iteratively revise classifier designs. Recent LLM-based agents have demonstrated the potential for automated model design, but when guided only by aggregate performance metrics, they lack insight into why individual cases fail and how the classifier should be revised. We present RecursiveECG, an evidence-driven LLM-as-Designer framework in which an LLM serves as an offline model designer that refines ECG classifiers based on concrete failures and objective ECG evidence. To ground failure diagnosis in executable evidence, Criteria-to-Measurement Compilation converts curated ECG criteria into validated deterministic functions that produce reproducible, reference-backed measurements for individual ECGs. Building on these measurements, Evidence-Grounded Failure Review analyzes failed and comparator cases by jointly considering raw waveforms, measurements, and model outputs, enabling the LLM to diagnose classifier limitations and formulate targeted revisions. Candidate revisions are executed and re-evaluated under a fixed problem contract, and only evidence-supported updates are retained. The resulting predictor is frozen after refinement and requires no LLM inference during deployment, while an audit trail links each accepted revision to its supporting evidence. Across PTB-XL, Georgia, and CPSC2018, RecursiveECG consistently outperforms strong baselines, achieving an average relative improvement of 10.0%. Extensive ablation and transfer studies further validate the effectiveness of its evidence-grounded refinement process.