"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"

"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support" - user: oncoagent-research tags: - oncology - multi-agent - LangGraph - RAG - QLoRA - AMD - open-source - clinical-ai - healthcare OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support Technical preprint · May 2026 · OncoAgent Research Group Abstract We present OncoAgent, an open-source, privacy-preserving clinical decision support system for oncology. OncoAgent combines a dual-tier fine-tuned LLM architecture with a state-of-the-art multi-agent LangGraph topology, a four-stage Corrective RAG pipeline over 70+ physician-grade NCCN and ESMO guidelines, and a three-layer reflexion safety validator enforcing a strict Zero-PHI policy. The system routes clinical queries through an additive complexity scorer to either a 9B parameter speed-optimised model (Tier 1) or a 27B deep-reasoning model (Tier 2), both fine-tuned via QLoRA on a corpus of 266,854 real and synthetically generated oncological cases using the Unsloth framework on AMD Instinct MI300X hardware (192 GB HBM3). Sequence packing on MI300X enabled full-dataset fine-tuning in approximately 50 minutes — a 56× throughput acceleration over API-based generation. Post-fix, CRAG document grading achieved a 100% success rate with a mean RAG confidence score of 2.3+. The complete system is 100% open source and deployable on-premises, eliminating proprietary cloud API dependency and preserving patient data sovereignty. Keywords: clinical decision support, oncology AI, multi-agent systems, retrieval-augmented generation, QLoRA, AMD ROCm, open-source healthcare AI, HITL safety, LangGraph, Corrective RAG 1. Introduction Oncology is one of the most information-dense and cognitively demanding domains in clinical medicine. The volume, heterogeneity, and rapid evolution of evidence-based guidelines — from the National Comprehensive Cancer Network (NCCN) to the European Society for Medical Oncology (ESMO) — create a persistent knowledge gap between published evidence and bedside practice. AI-assisted clinical decision support systems hold transformative potential for closing this gap, yet most commercially available systems fail in three critical ways: - Hallucinated recommendations not grounded in validated guidelines - Cloud API dependency that precludes on-premises deployment in privacy-sensitive hospital environments - Monolithic LLM architectures prone to context saturation under complex multi-comorbidity presentations OncoAgent is designed around three core principles: - Architectural decomposition: Clinical reasoning is decomposed across eight specialised LangGraph nodes, each with a bounded, auditable function. - Grounded generation: All model outputs are anchored to a curated vector knowledge base through a four-stage retrieval pipeline with explicit relevance gating. - Hardware sovereignty: The full inference and training stack runs natively on AMD Instinct MI300X using ROCm and open-source frameworks — enabling hospital deployment without data exfiltration. 2. Related Work 2.1 Clinical LLMs and Decision Support Large language models have demonstrated significant promise in clinical NLP tasks including diagnostic coding, literature summarisation, and patient communication. Domain-specific fine-tuning approaches — exemplified by BioMedLM, Med-PaLM 2, and ClinicalBERT — consistently improve performance on medical benchmarks over general-purpose models. OncoAgent extends this line of work by targeting the specific subdomain of oncological triage and treatment pathway recommendation, where hallucination consequences are most severe. 2.2 Multi-Agent Architectures Decomposed multi-agent systems have emerged as a principled approach to…