Metraipolis › archive › dc_57d613f16027

Continual Enterprise World Model Discovery in Dynamic Systems — arXiv:2609.19551

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19551
License (as archived)
CC0-1.0
Archived
2026-10-10T03:20:04.648Z
SHA-256 of the archived text
e47c67572ade0753479e36e36278705b242ec2ff59b2df1cb81ae74e7c8ffe3a
Stable URL of this page
https://metraipolis.com/documento/dc_57d613f16027

How to cite

Continual Enterprise World Model Discovery in Dynamic Systems — arXiv:2609.19551 — arXiv (en), https://arxiv.org/abs/2609.19551 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57d613f16027 (Metraipolis archive dc_57d613f16027, sha256 e47c67572ade0753479e36e36278705b242ec2ff59b2df1cb81ae74e7c8ffe3a)
BibTeX
@misc{dc57d613f16027,
  title = {Continual Enterprise World Model Discovery in Dynamic Systems — arXiv:2609.19551},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19551},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57d613f16027; sha256 e47c67572ade0753479e36e36278705b242ec2ff59b2df1cb81ae74e7c8ffe3a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19551. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platform but written by each organization and revised over time. An agent working in such a system cannot predict the result of its own actions without knowing these rules. We study continual enterprise world model discovery, where an agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes. From those observations it builds a world model, which it revises as the rules change. To evaluate this, we introduce EnterpriseWorldShift, built on a live ServiceNow environment with nine tables, 25 hidden rules and 600 evaluation actions. It presents four versions of the same enterprise world, with the tables and records held fixed while a rule is modified, then added, then removed, so that discovery, revision, extension and retirement are each tested in turn. Our Continual Discovery Agent (CDA) builds such a model and carries it from one world to the next. It predicts the effects of the hidden rules more accurately than looking them up for each question, the approach taken by prior work, by up to 8.98 IoU points, and it answers from its own model without querying the running system.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.19551 — 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 2026-10-10T03:04:13.618Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).