Metraipolis › archive › dc_49e7dd9e4fce

PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks — arXiv:2609.32685

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32685
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:54.480Z
SHA-256 of the archived text
6ba6e96132fefe75e6a192bdf9d3cebab66792334ff0edfa54d87663d3d3b0ac
Stable URL of this page
https://metraipolis.com/documento/dc_49e7dd9e4fce

How to cite

PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks — arXiv:2609.32685 — arXiv (en), https://arxiv.org/abs/2609.32685 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49e7dd9e4fce (Metraipolis archive dc_49e7dd9e4fce, sha256 6ba6e96132fefe75e6a192bdf9d3cebab66792334ff0edfa54d87663d3d3b0ac)
BibTeX
@misc{dc49e7dd9e4fce,
  title = {PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks — arXiv:2609.32685},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32685},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49e7dd9e4fce; sha256 6ba6e96132fefe75e6a192bdf9d3cebab66792334ff0edfa54d87663d3d3b0ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32685. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-informed neural networks (PINNs) provide a learning-based framework for solving partial differential equations (PDEs), yet their training behavior can change substantially throughout optimization. Residual distributions, gradient interactions, regional learning difficulty, and model-capacity requirements may evolve over time, while the network architecture and major training mechanisms are typically determined before training. We propose PINNMorph, an online PINN adaptation framework based on large language model (LLM)-guided policy evolution. PINNMorph maintains a population of state-conditioned adaptation policies that map execution diagnostics to controlled interventions over topology modification, additive representation augmentation, objective balancing, gradient handling, adaptive sampling, and optimizer-phase control. At each intervention opportunity, candidate programs are instantiated from the current policy population, selected according to the observed training state, and applied directly to the PINN under training. The resulting model inherits its existing parameters and training state and continues optimization along the same trajectory. Execution outcomes are subsequently used to evaluate interventions and evolve the policy population. Unlike pre-training architecture search or fixed adaptation rules, PINNMorph jointly adapts the current PINN and the policies governing its interventions using feedback from actual training. Experiments on 13 PDE benchmarks show that PINNMorph achieves lower solution errors than SA-PINN, ConFIG, RoPINN, HARMONIC, and PINNsAgent across all evaluated problems. Ablation studies further examine the effects of online adaptation, state-conditioned intervention selection, and execution-feedback-driven policy evolution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32685 — 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 2026-10-07T20:29:00.921Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).