Metraipolis › archive › dc_ca8bcf63264c

Trail: Accurate Local Smart Home Control Using Decision Models — arXiv:2611.00610

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00610
License (as archived): CC0-1.0
Archived: 2026-11-03T10:41:59.415Z
SHA-256 of the archived text: 0d563b0f5366bf4aa5febb0a50f20b221f6593f4580228b051c2a0631b789c64
Stable URL of this page: https://metraipolis.com/documento/dc_ca8bcf63264c

How to cite

Trail: Accurate Local Smart Home Control Using Decision Models — arXiv:2611.00610 — arXiv (en), https://arxiv.org/abs/2611.00610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca8bcf63264c (Metraipolis archive dc_ca8bcf63264c, sha256 0d563b0f5366bf4aa5febb0a50f20b221f6593f4580228b051c2a0631b789c64)

BibTeX

@misc{dcca8bcf63264c,
  title = {Trail: Accurate Local Smart Home Control Using Decision Models — arXiv:2611.00610},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00610},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca8bcf63264c; sha256 0d563b0f5366bf4aa5febb0a50f20b221f6593f4580228b051c2a0631b789c64},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Natural-language driven smart home control remains challenging: cloud-hosted Large Language Models (LLMs) raise privacy concerns, while local Small Language Models (SLMs) can generate invalid actions or misinterpret requests. We introduce Trail (Typed Registry-Anchored Inference for Language commands in Smart Homes), a fully local framework that replaces open-ended command generation with hierarchical typed decisions. Trail exploits the natural structure of a home's action space, selecting a room, device, and operation from candidates derived from the runtime device registry. This ensures valid actions while enabling confidence-based abstention when requests cannot be reliably resolved. We also design a structured memory module that uses typed decisions to support user preferences, device references, and multi-turn interactions. To evaluate Trail, we extend HomeBench and generate three datasets: Trek-Base, which tests natural-language variation; Trek-Robust, which evaluates robustness to changes in the home and its description; and Trek-Memory, which assesses conversational memory across multi-turn interactions. Trail achieves 85.3% accuracy on Trek-Robust versus 69.8% for a finetuned Qwen3.5-4B baseline, while remaining competitive on Trek-Base requests. With memory, Trail resolves 75.6% of the requests that depend on earlier turns, compared with 42.5% for the finetuned baseline given conversation history.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00610 — 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 2026-11-03T10:39:50.183Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).