Metraipolis › archive › dc_45efa9df2968
BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy Research — arXiv:2609.02729
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02729
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T04:44:31.421Z
- SHA-256 of the archived text
28a7cd8206f5105086e85e95703f5b8a8b4e2f9147c64049cd7b3a2c3757b588- Stable URL of this page
https://metraipolis.com/documento/dc_45efa9df2968
How to cite
BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy Research — arXiv:2609.02729 — arXiv (en), https://arxiv.org/abs/2609.02729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45efa9df2968 (Metraipolis archive dc_45efa9df2968, sha256 28a7cd8206f5105086e85e95703f5b8a8b4e2f9147c64049cd7b3a2c3757b588)
BibTeX
@misc{dc45efa9df2968,
title = {BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy Research — arXiv:2609.02729},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02729},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45efa9df2968; sha256 28a7cd8206f5105086e85e95703f5b8a8b4e2f9147c64049cd7b3a2c3757b588},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Occupants are a primary source of uncertainty in building energy consumption and management, yet existing occupant behavior models cannot capture adaptive and reasoning responses considering the occupant's personal history, current context, and the type of energy signal being delivered. This study presents BuildOcc, an open-source Python platform that grounds large language model agents in the American Time Use Survey (ATUS), a nationally representative diary dataset covering 16,684 respondents. Through BuildOcc, each simulated occupant agent can be instantiated with a demographic persona drawn from ATUS population statistics, a memory stream that accumulates and reflects on timestep-level observations, and an activity scheduler that samples empirically from ATUS time-at-activity distributions. The platform exposes a three-layer interface - Python library, REST API, and Model Context Protocol server - so that any building energy tool (EnergyPlus, Home Assistant) can integrate behavioral intelligence without bespoke coupling code. A plugin registry lets the community add new occupant strata, custom schedulers, and alternative memory backends as separate installable packages. Two validation tiers show that ATUS-grounded sampling reproduces empirically calibrated activity distributions and that demographic priors propagate into persona-consistent agent reasoning across timesteps, establishing internal consistency across strata. BuildOcc provides the building energy community with a reusable, openly available implementation of the occupant behavioral layer. BuildOcc is openly released at this https URL under the Apache License 2.0 and installable via pip install buildocc. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.02729 — 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 2026-10-17T04:09:22.119Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).