Metraipolis › archive › dc_65860bb6cde2

Network World Models as Environments for Algorithm Design on Complex Systems — arXiv:2610.01048

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01048
License (as archived)
CC0-1.0
Archived
2026-10-06T12:03:38.584Z
SHA-256 of the archived text
0a2d859a456d2057eac2a3f47d1af181bab28be956a3e8d35d3328a5a0bbaa12
Stable URL of this page
https://metraipolis.com/documento/dc_65860bb6cde2

How to cite

Network World Models as Environments for Algorithm Design on Complex Systems — arXiv:2610.01048 — arXiv (en), https://arxiv.org/abs/2610.01048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_65860bb6cde2 (Metraipolis archive dc_65860bb6cde2, sha256 0a2d859a456d2057eac2a3f47d1af181bab28be956a3e8d35d3328a5a0bbaa12)
BibTeX
@misc{dc65860bb6cde2,
  title = {Network World Models as Environments for Algorithm Design on Complex Systems — arXiv:2610.01048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_65860bb6cde2; sha256 0a2d859a456d2057eac2a3f47d1af181bab28be956a3e8d35d3328a5a0bbaa12},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems call for the same tool because the effect of an action is not immediate. Seeding nodes for a campaign, or immunizing nodes against an epidemic, changes little on its own; what matters is the outcome that unfolds over the steps that follow. Designing an algorithm that selects such actions to maximize expected performance on a task is inherently iterative, and every candidate must be scored by the outcome it produces. Obtaining that outcome has relied on simulation, whose cost becomes a bottleneck when candidates are evaluated over many sampled trajectories. We propose an action-conditioned Network World Model that learns a network's diffusion dynamics under interventions over time, applies each action to the network, and predicts the outcome that follows. It serves as a fast evaluator inside an algorithm design loop in which a coding agent designs and refines executable algorithms using feedback from full rollouts, action-level credit, and counterfactual probes over alternative interventions. Across eight network tasks and five diffusion models, the designed algorithms match or exceed the strongest reported baseline in 138 of 141 settings while enabling up to 14.5 times faster rollouts than Monte Carlo simulation. Code will be released upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.01048 — 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 2026-10-06T10:21:27.910Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).