Metraipolis › archive › dc_5d3965833b2d

COSMOS: Soft Mechanism Mixtures with Verifiable Routing for Long-Horizon PDE Forecasting — arXiv:2610.04427

Source
arXiv
Original
https://arxiv.org/abs/2610.04427
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:14.298Z
SHA-256 of the archived text
fd7df5bda3834d728aad2f3a2f14628a29db71c1a61b2881d773a031dbbf30fb
Stable URL of this page
https://metraipolis.com/documento/dc_5d3965833b2d

How to cite

COSMOS: Soft Mechanism Mixtures with Verifiable Routing for Long-Horizon PDE Forecasting — arXiv:2610.04427 — arXiv, https://arxiv.org/abs/2610.04427 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d3965833b2d (Metraipolis archive dc_5d3965833b2d, sha256 fd7df5bda3834d728aad2f3a2f14628a29db71c1a61b2881d773a031dbbf30fb)
BibTeX
@misc{dc5d3965833b2d,
  title = {COSMOS: Soft Mechanism Mixtures with Verifiable Routing for Long-Horizon PDE Forecasting — arXiv:2610.04427},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04427},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d3965833b2d; sha256 fd7df5bda3834d728aad2f3a2f14628a29db71c1a61b2881d773a031dbbf30fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04427. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural operators offer an efficient alternative to classical PDE solvers, but most learn a monolithic map per equation family and discretization. Real systems are compositional: transport, diffusion, wave, and reaction processes can act simultaneously. Existing mixture-of-experts operators typically use sparse top-$K$ routing, although concurrent physics is naturally a blend rather than a discrete choice. We propose COSMOS (Cooperative Operator Specialists with Mechanism-level Operator Soft-routing), a soft mechanism-mixture neural operator. Four process-biased specialists remain active at every step and are continuously mixed by a learned gate, with their features fused by a small network. Specialists share a coarse latent grid, while a zero-initialized full-resolution residual restores detail lost through the bottleneck. We also introduce an operator-splitting compositional benchmark with known mixture weights $w^\star$ per trajectory. Against family-tuned FNO under 20-step rollouts, an initial 3-seed evaluation suggested gains on diffusion--reaction, parity on Navier--Stokes, and weaker shallow-water performance. An 11-seed audit showed that the diffusion--reaction gain was unstable, motivating caution in small-seed rollout comparisons and precluding a reliable accuracy-win claim on these families. Ablations show that uniform routing or removing the specialist mixture substantially degrades stable-regime rollouts. On the labeled benchmark, dense soft routing yields $2.2\times$ lower error than hard top-1 routing at identical fusion; using generator weights $w^\star$ at inference further lowers rollout error to $0.034$, diagnosing limitations of the learned gate. However, routing labels do not align with the specialists' intended mechanisms: COSMOS supports compositional accuracy, not mechanism identity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04427 — 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 2026-10-06T05:24:05.857Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).