Abstract:Large language models (LLMs) have shown promise in clinical diagnosis but remain limited by unreliable report generation, weak evidence grounding, and opaque reasoning. We propose MedCollab, an IBIS-guided multi-agent framework for full-cycle clinical diagnosis and diagnostic report generation. Mimicking hospital consultation, MedCollab dynamically recruits specialist and exam agents from patient records. Each diagnostic hypothesis is structured through the Issue-Based Information System (IBIS) into evidence-linked arguments, improving traceability and auditability. MedCollab further constructs Hierarchical Disease Relation Chains (HDRC) to organize accepted hypotheses into clinically meaningful pathological and comorbidity relations. A verifier-guided consensus module audits reasoning quality, detects contradictions, and updates agent weights over multiple rounds. Experiments on ClinicalBench and MIMIC-IV show that MedCollab outperforms strong LLM and medical multi-agent baselines in diagnostic accuracy, department routing, evidence consistency, and report quality. These results demonstrate that structured argumentation and disease-relation modeling can improve the reliability, transparency, and clinical coherence of LLM-based diagnosis.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.01131 [cs.MA] |
| (or arXiv:2603.01131v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2603.01131 arXiv-issued DOI via DataCite |
From: Yuqi Zhan [view email]
[v1]
Sun, 1 Mar 2026 14:25:58 UTC (6,076 KB)
[v2]
Tue, 26 May 2026 16:23:05 UTC (9,684 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。