Metraipolis › archive › dc_f693154e2acb

Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language — arXiv:2608.04384

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04384
License (as archived)
CC0-1.0
Archived
2026-10-31T11:12:35.241Z
SHA-256 of the archived text
877bf8f9255f19a425499ced61538b6a583a9de289d91d25024ad36e6c488e9a
Stable URL of this page
https://metraipolis.com/documento/dc_f693154e2acb

How to cite

Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language — arXiv:2608.04384 — arXiv (en), https://arxiv.org/abs/2608.04384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f693154e2acb (Metraipolis archive dc_f693154e2acb, sha256 877bf8f9255f19a425499ced61538b6a583a9de289d91d25024ad36e6c488e9a)
BibTeX
@misc{dcf693154e2acb,
  title = {Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language — arXiv:2608.04384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f693154e2acb; sha256 877bf8f9255f19a425499ced61538b6a583a9de289d91d25024ad36e6c488e9a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural PDE solver auto-design is fundamentally a search-space representation problem. In the space of unrestricted Python programs, valid solvers form an extremely sparse subset: most candidate programs are syntactically incorrect, semantically incompatible, or numerically unstable. Direct code generation therefore forces an LLM to spend most of its search capacity navigating implementation failures rather than reasoning about solver quality. ADSL-PDE addresses this challenge by introducing a structured search state between solver concepts and executable code. It represents the functional decisions that determine a neural PDE solver (architecture, physical constraints, objectives, sampling, and optimization) while abstracting away low-level implementation details. A deterministic compiler maps each valid search state to an executable solver. In effect, ADSL-PDE reshapes the search space: it removes large regions of invalid programs, increases the density of meaningful candidates, and preserves the compositional freedom needed to discover previously unseen designs. Solver evolution can thus operate over design decisions rather than code artifacts. Built on this representation, our evolutionary agent iteratively proposes, evaluates, and refines solver search states using empirical feedback. Across multiple PDE benchmarks, ADSL-PDE improves both search efficiency and optimization stability, achieving an improvement of more than 52% within the first ten evolution iterations. These results suggest a broader principle for LLM-driven auto-design: effective agents do not merely require stronger reasoning, but rather a search representation that concentrates exploration on valid and consequential decisions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04384 — 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 2026-10-31T11:02:13.406Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).