Skip to content
Search
paperAugust 2026Unreviewed

MedCouncil: A Debate-Enabled Multi-Agent Framework for Second-Opinion Clinical Decision Support in General Internal Medicine

Santipong Thaiprayoon, Phattharat Songthung

2026 7th International Conference on Big Data Analytics and Practices (IBDAP)

View resource

Abstract

Large Language Models (LLMs) show promise in healthcare, but single-model systems often suffer from hallucinations, lack transparency, and have limited clinical safety. We present MedCouncil, a multi-agent framework designed to serve as a second-opinion tool for general internal medicine. Inspired by multidisciplinary consultations, MedCouncil orchestrates nine specialized clinical agents through a centralized supervisor agent. The system features a structured, multi-round Debate Mode that mimic

Categories

Agent Architecture

Cite

@inproceedings{thaiprayoon2026medcouncil,
  title = {{MedCouncil: A Debate-Enabled Multi-Agent Framework for Second-Opinion Clinical Decision Support in General Internal Medicine}},
  author = {Santipong Thaiprayoon and Phattharat Songthung},
  year = {2026},
  month = aug,
  booktitle = {2026 7th International Conference on Big Data Analytics and Practices (IBDAP)},
  doi = {10.1109/IBDAP69915.2026.11677991},
  url = {https://www.semanticscholar.org/paper/583373a0f86af92dd2097140781a7c8e4c37519b}
}