Tag
该论文提出一个基于本体引导的多智能体差分诊断框架，将诊断推理锚定在结构化的医学知识库上，通过显式、可审计的推理步骤减少幻觉并提升可解释性，同时自动生成追问以降低不确定性。
NSIDDx is a neuro-symbolic design framework for differential diagnosis in low-resource settings that prioritizes clinician collaboration and transparent reasoning, addressing gaps in LLM-based systems by ensuring verifiable outputs and auditability.
This arXiv paper introduces Social Chain of Thought (SCoT), a multi-agent architecture for medical differential diagnosis that structures multi-round specialist conversations. Evaluations show it outperforms single-agent and monolithic inference, particularly on the hardest diagnostic cases.
Introduces GuideSkill, an external reasoning layer that compiles clinical practice guidelines into executable diagnostic skills, improving LLM accuracy on clinical reasoning benchmarks without backbone updates.
AegisDx is a safety-oriented framework that uses specialized LLM components and verification gates for hypothetico-deductive clinical reasoning, improving differential diagnosis accuracy by 7-17 percentage points over standalone LLMs on medical case reports.
Proposes MedExpMem, an experience memory framework that enables medical vision-language models to accumulate and retrieve discriminative diagnostic experience from past cases, improving differential diagnosis accuracy by up to 7.0% on a radiology benchmark.