Metraipolis › archive › dc_d0cda4cdb540

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations — arXiv:2609.01257

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01257
License (as archived)
CC0-1.0
Archived
2026-10-17T06:32:22.227Z
SHA-256 of the archived text
58f8d3af01ad0f7cdd797c58bd5b602a0fe144f8f512ab15aba6844da83f77ba
Stable URL of this page
https://metraipolis.com/documento/dc_d0cda4cdb540

How to cite

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations — arXiv:2609.01257 — arXiv (en), https://arxiv.org/abs/2609.01257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0cda4cdb540 (Metraipolis archive dc_d0cda4cdb540, sha256 58f8d3af01ad0f7cdd797c58bd5b602a0fe144f8f512ab15aba6844da83f77ba)
BibTeX
@misc{dcd0cda4cdb540,
  title = {Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations — arXiv:2609.01257},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01257},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0cda4cdb540; sha256 58f8d3af01ad0f7cdd797c58bd5b602a0fe144f8f512ab15aba6844da83f77ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. While prior work has examined behavioral fidelity in survey responses and dialogue, longer-horizon real-world activity remains largely unexplored. We introduce a framework for evaluating behavioral fidelity in long-horizon activity simulations across temporal granularities and levels of analysis. As a case study, we collect a 43-hour multi-camera dataset of in-the-wild office activity and compare trace-derived conditioning mechanisms: persona descriptors, few-shot exemplars, and statistical transition and time-of-day priors. We find that behavioral fidelity is not uniform across metrics: statistical priors bring activity and sequence distributions closest to real behavior, yet over-fragment routines and suppress within-person variability. These findings motivate a more holistic evaluation that spans multiple metrics, temporal granularities, and levels of analysis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01257 — 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 2026-10-17T06:15:12.682Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).