MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

arXiv:2603.01131 · cs.MA, cs.AI · Submitted 2026-03-01 · Read on arXiv

cs.MA, cs.AI

Submitted: 2026-03-01

Updated: 2026-09-11

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 14× in this paper · explained in 2 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Differential Diagnosis — 12× in this paper
• Accuracy — 6× in this paper · explained in 1 episode
• Diagnostic Basis — 6× in this paper
• Hierarchical Disease Relation Chains — 5× in this paper
• Multi-Agent Framework — 5× in this paper · explained in 3 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Grounding — 4× in this paper · explained in 3 episodes
• Therapeutic Principle — 3× in this paper
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Issue-Based Information System — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Comprehensive Diagnostic Rate — 1× in this paper
• Department Classification Accuracy — 1× in this paper
• General Practitioner — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
• Qwen3 Technical Report
• Baichuan4-Finance Technical Report

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
• PeroMAS: A Multi-agent System of Perovskite Material Discovery
• StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning