Back

Med-ICE: Enhancing Factual Accuracy in Medical AI through Autonomous Multi-Agent Consensus

Chen, Z.; Wu, R.; Liu, Y.; Li, R.; Duprey, A.

2026-04-04 health informatics
10.64898/2026.04.02.26350080 medRxiv
Show abstract

The integration of Large Language Models into high-stakes clinical workflows is critically hampered by their lack of verifiable reliability and tendency to generate hallucinations. This paper introduces Med-ICE, an autonomous framework designed to enhance the reliability of LLMs for medical applications. Med-ICE adapts the Iterative Consensus Ensemble paradigm, enabling a group of peer LLM agents to collaboratively converge on a final answer through iterative rounds of generation and peer review, thereby eliminating the need for an external arbiter and its associated scalability bottleneck. Our work makes three key contributions: (1) a novel semantic consensus mechanism that determines agreement based on semantic similarity, crucial for nuanced clinical language; (2) demonstration of state-of-the-art performance, where Med-ICE significantly outperforms both direct single-LLM generation and the Self-Refinement technique on challenging medical benchmarks; and (3) a highly efficient and scalable architecture, as our Semantic Consensus Monitor is computationally lightweight. This research establishes a new standard for developing safer, more trustworthy LLM systems, paving the way for their responsible integration into medicine.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
npj Digital Medicine
97 papers in training set
Top 0.2%
18.6%
2
IEEE Journal of Biomedical and Health Informatics
34 papers in training set
Top 0.1%
12.3%
3
Scientific Reports
3102 papers in training set
Top 11%
8.2%
4
PLOS ONE
4510 papers in training set
Top 29%
6.3%
5
iScience
1063 papers in training set
Top 2%
4.8%
50% of probability mass above
6
Nature Communications
4913 papers in training set
Top 40%
3.6%
7
Nature Medicine
117 papers in training set
Top 1%
3.1%
8
Journal of Biomedical Informatics
45 papers in training set
Top 0.5%
3.1%
9
Bioinformatics
1061 papers in training set
Top 6%
2.9%
10
Nature Machine Intelligence
61 papers in training set
Top 1%
2.3%
11
Journal of the American Medical Informatics Association
61 papers in training set
Top 1%
2.1%
12
Computers in Biology and Medicine
120 papers in training set
Top 2%
1.7%
13
PLOS Digital Health
91 papers in training set
Top 2%
1.5%
14
Journal of Medical Internet Research
85 papers in training set
Top 3%
1.5%
15
BMC Medical Informatics and Decision Making
39 papers in training set
Top 2%
1.3%
16
Artificial Intelligence in Medicine
15 papers in training set
Top 0.4%
1.3%
17
Patterns
70 papers in training set
Top 2%
0.9%
18
Advanced Science
249 papers in training set
Top 16%
0.9%
19
Med
38 papers in training set
Top 0.7%
0.8%
20
BMC Bioinformatics
383 papers in training set
Top 7%
0.7%
21
International Journal of Medical Informatics
25 papers in training set
Top 2%
0.7%
22
Journal of Personalized Medicine
28 papers in training set
Top 1%
0.7%
23
Nature Computational Science
50 papers in training set
Top 2%
0.7%
24
GigaScience
172 papers in training set
Top 3%
0.7%
25
Computer Methods and Programs in Biomedicine
27 papers in training set
Top 1%
0.6%
26
Heliyon
146 papers in training set
Top 8%
0.6%
27
Communications Biology
886 papers in training set
Top 29%
0.6%