MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments

Researchers propose MA-RAG, a multi-agent retrieval-augmented generation framework that improves factual correctness in summarizing longitudinal Parkinson's disease assessments, achieving up to a 122% relative increase in Fact Precision (from 0.436 to 0.990) and reducing Hallucination Rate by up to 98% (from 0.564 to 0.010) compared to baselines, according to an arXiv paper (2608.28624v1).

arXiv:2608.28624v1 Announce Type: new Abstract: Accurate interpretation of single-visit and longitudinal clinical assessments for Parkinson's disease is time-consuming and often depends on specialist expertise. Although large language models LLMs can generate natural language summaries, they frequently lack domain-specific clinical grounding and struggle to produce factually correct and temporally consistent responses for structured longitudinal assessment data. To address these limitations, we propose MA-RAG, a query-driven multi-agent retrieval-augmented generation framework that decomposes clinical reasoning into domain-specialized agents, combines structured fact extraction, and synthesizes clinically grounded summaries through a final verification stage. The framework supports four clinical analysis tasks: single-session, trajectory, comparison, and cohort summarization. We evaluate MA-RAG using objective metrics, namely Fact Precision, Hallucination Rate, Temporal Fidelity, and Semantic Similarity, together with subjective evaluations conducted by clinical experts. Compared to Traditional, RAG-only, and Single-agent RAG baselines, MA-RAG substantially improves factual correctness, achieving up to a 122% relative increase in Fact Precision from 0.436 to 0.990 and reducing the Hallucination Rate by up to 98% from 0.564 to 0.010 , while consistently receiving top ratings from clinical experts for organization and clinical usefulness. These results demonstrate that domain-specialized multi-agent reasoning enables reliable query-driven summarization of structured longitudinal clinical assessment data.