Metraipolis › archive › dc_0481bbd47df3

Toward Personalized Sleep Guidance from Wearable Data Using Language Models — arXiv:2609.22463

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.22463
License (as archived): CC0-1.0
Archived: 2026-10-09T06:49:30.888Z
SHA-256 of the archived text: e13c815010891497693ccffce0c8199f88da3a5c9fba8420f23ef61135d58047
Stable URL of this page: https://metraipolis.com/documento/dc_0481bbd47df3

How to cite

Toward Personalized Sleep Guidance from Wearable Data Using Language Models — arXiv:2609.22463 — arXiv (en), https://arxiv.org/abs/2609.22463 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0481bbd47df3 (Metraipolis archive dc_0481bbd47df3, sha256 e13c815010891497693ccffce0c8199f88da3a5c9fba8420f23ef61135d58047)

BibTeX

@misc{dc0481bbd47df3,
  title = {Toward Personalized Sleep Guidance from Wearable Data Using Language Models — arXiv:2609.22463},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22463},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0481bbd47df3; sha256 e13c815010891497693ccffce0c8199f88da3a5c9fba8420f23ef61135d58047},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22463. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering remain insufficient for personalized sleep guidance. Training specialized models, however, often requires costly expert annotation. Moreover, privacy and accessibility concerns motivate lightweight, local deployment for end users. We present a two-stage framework to address these challenges. Specifically, in Stage~1, a multi-agent LLM pipeline reasons structured sleep guidance from unannotated wearable records, enabling scalable dataset construction. Stage~2 distills guidance reasoning trajectories into small language models (SLMs) through supervised fine-tuning and integrates a training-free Best-of-$N$ selection strategy to enhance inference. Experimental results demonstrate our method outperforms commercial general and medical LLMs and open-source models. Human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.22463 — 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 2026-10-09T06:48:44.932Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).