Metraipolis › archive › dc_1bfb8ef55a7a
GAV: A scientific experimentation environment for PDE agents — arXiv:2610.30292
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30292
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T08:33:49.246Z
- SHA-256 of the archived text
55d2a275405328eec4841db990d2a805b8aa293fab208b73282bffe36986a81f- Stable URL of this page
https://metraipolis.com/documento/dc_1bfb8ef55a7a
How to cite
GAV: A scientific experimentation environment for PDE agents — arXiv:2610.30292 — arXiv (en), https://arxiv.org/abs/2610.30292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1bfb8ef55a7a (Metraipolis archive dc_1bfb8ef55a7a, sha256 55d2a275405328eec4841db990d2a805b8aa293fab208b73282bffe36986a81f)
BibTeX
@misc{dc1bfb8ef55a7a,
title = {GAV: A scientific experimentation environment for PDE agents — arXiv:2610.30292},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30292},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1bfb8ef55a7a; sha256 55d2a275405328eec4841db990d2a805b8aa293fab208b73282bffe36986a81f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable feedback is essential for coding agents to develop programs for partial differential equations (PDEs). Yet evaluating these programs on new PDE problems often requires expensive reference computations, while fixed datasets restrict the range of experiments. We introduce Generator-Agent-Verifier (GAV), a scientific experimentation environment that makes new PDE problems verifiable by construction. The Generator learns a distribution of continuous reference solutions using data from numerical simulations or experimental measurements to represent a target physical regime. Using the method of manufactured solutions, it works backward from the generated reference solutions to construct matching PDE problems without a separate numerical solve. The Agent designs experiments, investigates failures, and iteratively improves its program. The Verifier evaluates candidate programs against the reference solutions and provides numerical feedback on accuracy and computational cost. This feedback can also guide the generation of new problems that probe the current program's weaknesses. We provide a theoretical analysis of evaluation reliability and guided development. Experiments on Navier-Stokes and Vlasov-Poisson-type equations across different data sources and regimes demonstrate the effectiveness of GAV. In particular, on the numerical Navier-Stokes task, GAV reduces the mean test error of three existing PDE agents by more than an order of magnitude relative to their original setups. Code is available at this https URL . 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/2610.30292 — 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 2026-10-25T08:31:13.133Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).