mlsanityData to 14 Oct 2026

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

arXiv 2608.28624 ↗First posted 30 Jul 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 37 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

8 of 37 references.

References · 8

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  5. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 493
  6. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  7. 2025Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Predictioncited by 12
  8. 2025Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answeringcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison
  2. 2026PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation
  3. 2026The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
  4. 2026ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations
  5. 2026Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation
  6. 2025A Multi-Agent Approach to Neurological Clinical Reasoning
  7. 2026AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
  8. 2024Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology