Metraipolis › archive › dc_ebcb4b1d30ef

Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation — arXiv:2608.19778

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.19778
License (as archived): CC0-1.0
Archived: 2026-10-18T11:36:37.387Z
SHA-256 of the archived text: 272bb1de4ccf66e043927dfe9ae1a65cc9cafde7579a25161f7783883ec75c6f
Stable URL of this page: https://metraipolis.com/documento/dc_ebcb4b1d30ef

How to cite

Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation — arXiv:2608.19778 — arXiv (en), https://arxiv.org/abs/2608.19778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebcb4b1d30ef (Metraipolis archive dc_ebcb4b1d30ef, sha256 272bb1de4ccf66e043927dfe9ae1a65cc9cafde7579a25161f7783883ec75c6f)

BibTeX

@misc{dcebcb4b1d30ef,
  title = {Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation — arXiv:2608.19778},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19778},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebcb4b1d30ef; sha256 272bb1de4ccf66e043927dfe9ae1a65cc9cafde7579a25161f7783883ec75c6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pedestrian simulators need a behaviour rule for every agent, but privacy usually limits the data for setting one to aggregate statistics, namely zone-level device counts and origin-to-destination (OD) flows, with no individual trajectories. Such aggregates under-determine individual behaviour, because many different sets of decisions reproduce the same counts. We fine-tune a language model crowd agent so that the simulated population matches the observed destination composition, the fraction of the departing crowd heading to each point of interest. We read this target from the OD flow and reweight the model's own destination distribution onto it by iterative proportional fitting. Because fine-tuning inflates the dominant destination class, we fit the low-rank adapter to trajectories resampled to a corrected training composition that reaches the target after this inflation. On mobile network counts from two baseball games the fine-tuned agent runs without inference-time correction, cutting the destination-share error by 25%, while the grid correlation remains similar across policies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.19778 — 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 2026-10-18T11:30:10.497Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).