{"slug": "ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis", "title": "Ontology-guided multi-agent reasoning for explainable differential diagnosis", "summary": "A team of researchers posted arXiv paper 2610.36325v1, an ontology-guided multi-agent framework for differential diagnosis that grounds LLM diagnostic inference in a structured, expert-curated medical knowledge base to reduce hallucination and make reasoning auditable. The framework decomposes diagnosis into explicit reasoning steps, constrains inference to evidence-backed associations, and identifies the most discriminative missing symptoms to generate targeted follow-up questions. The authors report the approach improves diagnostic transparency, traceability, consistency and accuracy, and released the source code publicly.", "body_md": "arXiv:2610.36325v1 Announce Type: new \nAbstract: Effective differential diagnosis depends on well structured and unambiguous patient case descriptions, since incomplete or ambiguous clinical information readily leads to diagnostic errors and inconsistent reasoning. Large Language Models (LLMs) have recently shown promising capabilities in medical question answering and clinical reasoning; however, even when achieving competitive performance on medical benchmarks, they often rely on pattern recognition learned from training data rather than grounded clinical evidence, and can generate plausible yet unsupported diagnostic conclusions. Their reasoning remains largely opaque, making it difficult for clinicians to assess the evidence and rationale behind a given recommendation. To address this gap, we propose an ontology-guided, multiagent differential diagnosis framework that replicates the iterative reasoning process of physicians. The framework grounds diagnostic inference in a structured, expert-curated medical knowledge base, enabling interpretation of symptoms, clinical findings, or disease relationships, while decomposing diagnosis into explicit, auditable reasoning steps. This ontology-based grounding constrains inference to evidence-backed associations, reducing hallucination and improving diagnostic transparency, traceability, and consistency. The system then identifies the most discriminative missing symptoms and generates targeted follow-up questions to reduce uncertainty through a process that mirrors to clinical inquiry. Together, these components improve the reliability, explainability, and diagnostic accuracy of AI-assisted differential diagnosis. The source code is publicly available.", "url": "https://wpnews.pro/news/ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis", "canonical_source": "https://arxiv.org/abs/2610.36325", "published_at": "2026-10-28 04:00:00+00:00", "updated_at": "2026-10-28 04:11:49.602827+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "large-language-models", "ai-research", "ai-safety"], "entities": ["arXiv", "2610.36325v1"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis", "markdown": "https://wpnews.pro/news/ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis.md", "text": "https://wpnews.pro/news/ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis.txt", "jsonld": "https://wpnews.pro/news/ontology-guided-multi-agent-reasoning-for-explainable-differential-diagnosis.jsonld"}}