# Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

arXiv: https://arxiv.org/abs/2512.09944 · HTML: https://mlsanity.com/paper/2512.09944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MedSAM2: Segment Anything in 3D Medical Images and Videos](https://mlsanity.com/paper/2504.03600/) (2025)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [MedRAX: Medical Reasoning Agent for Chest X-ray](https://mlsanity.com/paper/2502.02673/) (2025)
- [EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation](https://mlsanity.com/paper/2410.09704/) (2024)
- [Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers](https://mlsanity.com/paper/2504.19254/) (2025)
- [EchoApex: A General-Purpose Vision Foundation Model for Echocardiography](https://mlsanity.com/paper/2410.11092/) (2024)
- [MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction](https://mlsanity.com/paper/2510.03687/) (2025)
- [How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?](https://mlsanity.com/paper/2504.14391/) (2025)
- [EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation](https://mlsanity.com/paper/2511.13948/) (2025)

## Abstract (arXiv)

Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, yet existing foundation-model pipelines largely solve isolated subtasks and fail when tool outputs are noisy or values fall near clinical cutoffs. We propose Echo-CoPilot, an end-to-end agentic framework that combines a multi-perspective workflow with knowledge-graph-guided measurement selection. Echo-CoPilot runs three independent ReAct-style agents, structural, pathological, and quantitative, that invoke specialized echocardiography tools to extract parameters while querying EchoKG to determine which measurements are required for the clinical question and which should be avoided. A self-contrast language model then compares the evidence-grounded perspectives, generates a discrepancy checklist, and re-queries EchoKG to apply the appropriate guideline thresholds and resolve conflicts, reducing hallucinated measurement selection and borderline flip-flops. On MIMICEchoQA, Echo-CoPilot provides higher accuracy compared to SOTA baselines and, under a stochasticity stress test, achieves higher reliability through more consistent conclusions and fewer answer changes across repeated runs. Our code is publicly available at https://github.com/moeinheidari7829/Echo-CoPilot.