Evaluation of Multi-Agent LLMs in Multidisciplinary Team Decision-Making for Challenging Cancer Cases
Published in Machine Learning for Healthcare (MLHC), 2025
This paper investigates the effectiveness of multi-agent large language model systems in collaborative medical decision-making scenarios, specifically focusing on challenging cancer cases that require multidisciplinary team consultation. We evaluate how different AI agents can simulate the roles of various medical specialists and collaborate to reach consensus decisions.
Research Contributions:
- Novel framework for multi-agent LLM collaboration in medical decision-making
- Comprehensive evaluation on challenging cancer case datasets
- Analysis of agent interaction patterns and decision quality
- Insights into AI-assisted multidisciplinary medical consultations
Keywords: Multi-Agent Systems, Large Language Models, Medical AI, Cancer Diagnosis, Collaborative Decision-Making
Note: Paper accepted at MLHC 2025 ( indicates equal contribution)*
Recommended citation: Jaesik Kim*, Byounghan Lee*, Kyung-Ah Sohn, Dokyoon Kim, Young Chan Lee. (2025). "Evaluation of Multi-Agent LLMs in Multidisciplinary Team Decision-Making for Challenging Cancer Cases." Machine Learning for Healthcare (MLHC).