# RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis

arXiv: https://arxiv.org/abs/2602.01297 · HTML: https://mlsanity.com/paper/2602.01297/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 6 of its 47 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Placed in

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

## Builds on (most cited first, 6 of 6)

- [AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator](https://mlsanity.com/paper/2402.09742/) (2024)
- [MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring](https://mlsanity.com/paper/2512.24181/) (2025)
- [CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs](https://mlsanity.com/paper/2601.11047/) (2026)
- [Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.01844/) (2026)
- [Paging Dr. GPT: Extracting Information from Clinical Notes to Enhance Patient Predictions](https://mlsanity.com/paper/2504.12338/) (2025)
- [From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation](https://mlsanity.com/paper/2508.00581/) (2025)

## Built on by (most cited first, 1 of 1)

- [PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical Flowcharts](https://mlsanity.com/paper/2605.25970/) (2026)

## Abstract (arXiv)

Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for large language models (LLMs) in clinical diagnosis. In such settings, single-agent systems are vulnerable to self-reinforcing errors, as their predictions lack independent validation and can drift toward spurious conclusions. Although recent multi-agent frameworks attempt to mitigate this issue through collaborative reasoning, their interactions are often shallow and loosely structured, failing to reflect the rigorous, evidence-driven processes used by clinical experts. More fundamentally, existing approaches largely ignore the rich logical dependencies among diseases, such as mutual exclusivity, pathological compatibility, and diagnostic confusion. This limitation prevents them from ruling out clinically implausible hypotheses, even when sufficient evidence is available. To overcome these, we propose RE-MCDF, a relation-enhanced multi-expert clinical diagnosis framework. RE-MCDF introduces a generation--verification--revision closed-loop architecture that integrates three complementary components: (i) a primary expert that generates candidate diagnoses and supporting evidence, (ii) a laboratory expert that dynamically prioritizes heterogeneous clinical indicators, and (iii) a multi-relation awareness and evaluation expert group that explicitly enforces inter-disease logical constraints. Guided by a medical knowledge graph (MKG), the first two experts adaptively reweight EMR evidence, while the expert group validates and corrects candidate diagnoses to ensure logical consistency. Extensive experiments on the neurology subset of CMEMR (NEEMRs) and on our curated dataset (XMEMRs) demonstrate that RE-MCDF consistently outperforms state-of-the-art baselines in complex diagnostic scenarios (https://github.com/shenshaowei/RE-MCDF).