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

2026-03-01

AI Summary

This work addresses the challenges of hallucination and opaque reasoning in large language models (LLMs) for clinical diagnosis by proposing a causal-driven multi-agent collaborative framework that emulates a hospital’s multi-tier consultation process. The framework dynamically recruits specialized diagnostic and examination agents, integrating structured IBIS (Issue-Based Information System) argumentation with hierarchical disease causal chain modeling to enable end-to-end, traceable diagnostic reasoning. This approach substantially enhances transparency and clinical compliance. Experimental results on real-world clinical datasets demonstrate that the proposed method significantly outperforms both standalone LLMs and existing medical multi-agent systems in terms of Accuracy and RaTEScore, effectively mitigating medical hallucinations.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large language models (LLMs) have shown promise in healthcare applications, however, their use in clinical practice is still limited by diagnostic hallucinations and insufficiently interpretable reasoning. We present MedCollab, a novel multi-agent framework that emulates the hierarchical consultation workflow of modern hospitals to autonomously navigate the full-cycle diagnostic process. The framework incorporates a dynamic specialist recruitment mechanism that adaptively assembles clinical and examination agents according to patient-specific symptoms and examination results. To ensure the rigor of clinical work, we adopt a structured Issue-Based Information System (IBIS) argumentation protocol that requires agents to provide ``Positions'' backed by traceable evidence from medical knowledge and clinical data. Furthermore, the framework constructs a Hierarchical Disease Causal Chain that transforms flattened diagnostic predictions into a structured model of pathological progression through explicit logical operators. A multi-round Consensus Mechanism iteratively filters low-quality reasoning through logic auditing and weighted voting. Evaluated on real-world clinical datasets, MedCollab significantly outperforms pure LLMs and medical multi-agent systems in Accuracy and RaTEScore, demonstrating a marked reduction in medical hallucinations. These findings indicate that MedCollab provides an extensible, transparent, and clinically compliant approach to medical decision-making.

Problem

• diagnostic hallucinations
• interpretable reasoning
• clinical diagnosis
• medical decision-making
• LLM limitations

Innovation

• Causal-Driven Multi-Agent Collaboration
• IBIS-Structured Argumentation
• Hierarchical Disease Causal Chain
• Dynamic Specialist Recruitment
• Consensus Mechanism