Metraipolis › archive › dc_0bdecb408a1a

MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments — arXiv:2608.28624

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28624
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:07.543Z
SHA-256 of the archived text
577371b934666ee3235cc6a1f2a6d8daa31eaf178c7fc1bd06cfe5b79947a1ab
Stable URL of this page
https://metraipolis.com/documento/dc_0bdecb408a1a

How to cite

MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments — arXiv:2608.28624 — arXiv (en), https://arxiv.org/abs/2608.28624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bdecb408a1a (Metraipolis archive dc_0bdecb408a1a, sha256 577371b934666ee3235cc6a1f2a6d8daa31eaf178c7fc1bd06cfe5b79947a1ab)
BibTeX
@misc{dc0bdecb408a1a,
  title = {MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments — arXiv:2608.28624},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28624},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bdecb408a1a; sha256 577371b934666ee3235cc6a1f2a6d8daa31eaf178c7fc1bd06cfe5b79947a1ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28624 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.663Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).