# Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)

arXiv: https://arxiv.org/abs/2607.05032 · HTML: https://mlsanity.com/paper/2607.05032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 50 of its 112 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 30 of 50)

- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification](https://mlsanity.com/paper/2404.00762/) (2024)
- [TOGA: A Neural Method for Test Oracle Generation](https://mlsanity.com/paper/2109.09262/) (2021)
- [Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?](https://mlsanity.com/paper/2310.01831/) (2023)
- [A3Test: Assertion-Augmented Automated Test Case Generation](https://mlsanity.com/paper/2302.10352/) (2023)
- [TOGLL: Correct and Strong Test Oracle Generation with LLMs](https://mlsanity.com/paper/2405.03786/) (2024)
- [Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting](https://mlsanity.com/paper/2304.11686/) (2023)
- [Large Language Models and Video Games: A Preliminary Scoping Review](https://mlsanity.com/paper/2403.02613/) (2024)
- [A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing](https://mlsanity.com/paper/2412.16620/) (2024)
- [LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs](https://mlsanity.com/paper/2404.10304/) (2024)
- [Test Oracle Automation in the era of LLMs](https://mlsanity.com/paper/2405.12766/) (2024)
- [ClassInvGen: Class Invariant Synthesis using Large Language Models](https://mlsanity.com/paper/2502.18917/) (2025)
- [Doc2OracLL: Investigating the Impact of Documentation on LLM-based Test Oracle Generation](https://mlsanity.com/paper/2412.09360/) (2024)
- [Neural-Based Test Oracle Generation: A Large-scale Evaluation and Lessons Learned](https://mlsanity.com/paper/2307.16023/) (2023)
- [Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation](https://mlsanity.com/paper/2506.02943/) (2025)
- [Towards More Realistic Evaluation for Neural Test Oracle Generation](https://mlsanity.com/paper/2305.17047/) (2023)
- [Assessing Evaluation Metrics for Neural Test Oracle Generation](https://mlsanity.com/paper/2310.07856/) (2023)
- [Towards Generating Executable Metamorphic Relations Using Large Language Models](https://mlsanity.com/paper/2401.17019/) (2024)
- [AsserT5: Test Assertion Generation Using a Fine-Tuned Code Language Model](https://mlsanity.com/paper/2502.02708/) (2025)
- [Are Autonomous Web Agents Good Testers?](https://mlsanity.com/paper/2504.01495/) (2025)
- [A Tale of 1001 LoC: Potential Runtime Error-Guided Specification Synthesis for Verifying Large-Scale Programs](https://mlsanity.com/paper/2512.24594/) (2025)
- [Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries](https://mlsanity.com/paper/2406.07944/) (2024)
- [Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy](https://mlsanity.com/paper/2411.08254/) (2024)
- [AugmenTest: Enhancing Tests with LLM-Driven Oracles](https://mlsanity.com/paper/2501.17461/) (2025)
- [Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models](https://mlsanity.com/paper/2502.16071/) (2025)
- [WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements](https://mlsanity.com/paper/2602.11724/) (2026)
- [METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries](https://mlsanity.com/paper/2502.02794/) (2025)
- [Acceptance Test Generation with Large Language Models: An Industrial Case Study](https://mlsanity.com/paper/2504.07244/) (2025)

## Abstract (arXiv)

Background: Disease severity is a multidimensional construct difficult to capture with rule-based approaches in Electronic Healthcare Records (EHR). Agentic large language model (LLM) systems could synthesise clinical evidence and reason over EHRs, but remain unevaluated for this task. Methods: MOSAIC is a two-phase agentic LLM framework for severity phenotyping, using type 2 diabetes (T2D) as a proof-of-concept. MOSAIC was evaluated on a synthetic cohort (SyntheticMass; open-weight N = 4,886; closed-weight N = 200) against three algorithmic ground truths (DCSI, DiSSCo, Cooper) and against all-cause mortality and incident complications. Open-weight (locally deployable) and proprietary pipelines were also compared. Results: The generated framework spanned domains absent from the comparators, including biomarker-based glycaemic staging, beta-cell function, and social determinants of health. Open-weight MOSAIC matched the proprietary pipeline (closed- vs open-weight weighted kappa = 0.773) and reached moderate agreement with Cooper (kappa = 0.597) and DCSI (kappa = 0.534) and fair agreement with DiSSCo (kappa = 0.320). Agent-based (Type 1) tiers showed significant separation of all-cause mortality (log-rank p < 0.001; crude hazard ratios 1.6-2.4 for non-Baseline tiers), with non-monotonic separation at the upper tiers, and an inverse gradient for incident complications (log-rank p < 0.001) consistent with depletion of susceptibles. Agentic classification also diverged from deterministic execution of the same rubric (MOSAIC Frozen; kappa = 0.428), indicating reasoning beyond fixed rules. Conclusion: MOSAIC shows agentic LLM systems can generate and apply clinically meaningful severity phenotypes from structured EHR data in T2D. Extending it to other diseases with similarly multidimensional severity warrants further research.