Metraipolis › archive › dc_e7e93cdf05df
The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study — arXiv:2610.32151
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32151
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:51:44.345Z
- SHA-256 of the archived text
8dae5e1ce2991982c0a97641b70a7b9d7d6ae9228c2c4d8c380e2d74f698a0ef- Stable URL of this page
https://metraipolis.com/documento/dc_e7e93cdf05df
How to cite
The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study — arXiv:2610.32151 — arXiv (en), https://arxiv.org/abs/2610.32151 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e7e93cdf05df (Metraipolis archive dc_e7e93cdf05df, sha256 8dae5e1ce2991982c0a97641b70a7b9d7d6ae9228c2c4d8c380e2d74f698a0ef)
BibTeX
@misc{dce7e93cdf05df,
title = {The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study — arXiv:2610.32151},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32151},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e7e93cdf05df; sha256 8dae5e1ce2991982c0a97641b70a7b9d7d6ae9228c2c4d8c380e2d74f698a0ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32151. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model agents that use tools could take on part of the electronic health record and desk work that occupies physicians' time, but in many hospitals the medical information systems run inside closed networks, so the model and the agent harness must also sit inside. We designed, implemented, and deployed LLENS, a clinical support AI agent platform that runs inside the closed network of Hokkaido University Hospital on one host with 8 NVIDIA H200 GPUs, the open-weight model Kimi K2.6 (~1 trillion parameters), and a web application rebuilt from Open WebUI. The harness has 10 components, including page image reading, full-text attachment input, a path-addressed document tree without a vector index, a network-isolated sandbox, artifact return, self-checking of generated output, subagents, and saved procedures. Kimi K2.6 was chosen from 3 open-weight candidates and scored 480/500 on the 2026 Japanese Medical Licensing Examination; it generated 119 tokens/s for one user and served 16 concurrent requests at 908 tokens/s in total. On 180 questions over hospital documents (3 seeds each), mean accuracy was 10.7% with no documents, 81.3% with fixed retrieval (top 10 chunks of one lexical search), and 97.2% with interactive access, in which the model reads with document tools and the sandbox (15.9 percentage points above fixed retrieval, 95% CI 10.9-21.3); the difference lay in filtering/counting questions (16.7% vs 87.8%). Five scenarios with synthetic data ran on combinations of the components: needlestick injury response, batch adverse event grading, scanned referral letter transcription, falls data aggregation and plotting, and investigation of 3 topics by subagents. The platform has run on the hospital network since September 14, 2026. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.32151 — 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 2026-10-26T19:45:33.391Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).