MedCollab: Causal-Driven Multi-Agent Collaboration for Full-Cycle Clinical Diagnosis via IBIS-Structured Argumentation

Researchers have developed MedCollab, a multi-agent AI framework that uses structured argumentation and causal reasoning to improve clinical diagnosis accuracy. The system outperforms traditional LLMs by reducing medical hallucinations and providing more transparent, clinically compliant diagnostic processes through hierarchical consultation workflows.

• →MedCollab introduces a novel multi-agent framework that mimics hospital consultation workflows for autonomous clinical diagnosis.
• →The system uses Issue-Based Information System (IBIS) argumentation requiring agents to provide evidence-backed medical positions.
• →A Hierarchical Disease Causal Chain transforms diagnostic predictions into structured pathological progression models.
• →The framework significantly outperforms pure LLMs and existing medical multi-agent systems in accuracy metrics.
• →MedCollab demonstrates marked reduction in medical hallucinations while providing transparent and clinically compliant decision-making.