Metraipolis › archive › dc_2de90090e577

EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse — arXiv:2609.15161

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15161
License (as archived): CC0-1.0
Archived: 2026-10-15T22:53:40.946Z
SHA-256 of the archived text: 9b3deb2363b9c1cfaeb8a03f5f110b1177a888bf62150d7677cfe0b52c694894
Stable URL of this page: https://metraipolis.com/documento/dc_2de90090e577

How to cite

EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse — arXiv:2609.15161 — arXiv (en), https://arxiv.org/abs/2609.15161 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2de90090e577 (Metraipolis archive dc_2de90090e577, sha256 9b3deb2363b9c1cfaeb8a03f5f110b1177a888bf62150d7677cfe0b52c694894)

BibTeX

@misc{dc2de90090e577,
  title = {EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse — arXiv:2609.15161},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15161},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2de90090e577; sha256 9b3deb2363b9c1cfaeb8a03f5f110b1177a888bf62150d7677cfe0b52c694894},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15161. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strategies and lack persistent clinical memory, preventing self-evolving from prior diagnostic successes and failures. We present EMR, a self-evolving medical multi-agent system via Experience Mining and Reuse. EMR introduces a hierarchical clinical experience library that organizes accumulated knowledge into three levels: clinical principles, diagnostic patterns, and representative cases. During inference, EMR emulates multidisciplinary consultation: a planner agent coordinates domain-specific department agents for specialized reasoning, while a summary agent synthesizes their analyses into a final decision. Critically, EMR automatically extracts correct diagnostic insights and failure-related warnings from multi-agent reasoning trajectories, incrementally updating the experience library to guide future cases. Experiments on medical reasoning benchmarks demonstrate that EMR consistently outperforms state-of-the-art medical multi-agent baselines. Further analysis reveals that the hierarchical experience enables cross-specialty generalization and transfer across diverse LLM backbones, offering a scalable and in

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.15161 — 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 2026-10-15T22:29:03.821Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).