Metraipolis › archive › dc_7ef558f88164

See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs — arXiv:2608.27869

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27869
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:16.594Z
SHA-256 of the archived text
da084cfdf7cc81db0f31f1886dc977fc1ac1ebe6addedf6a59efe2b9802ed4f5
Stable URL of this page
https://metraipolis.com/documento/dc_7ef558f88164

How to cite

See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs — arXiv:2608.27869 — arXiv (en), https://arxiv.org/abs/2608.27869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ef558f88164 (Metraipolis archive dc_7ef558f88164, sha256 da084cfdf7cc81db0f31f1886dc977fc1ac1ebe6addedf6a59efe2b9802ed4f5)
BibTeX
@misc{dc7ef558f88164,
  title = {See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs — arXiv:2608.27869},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27869},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ef558f88164; sha256 da084cfdf7cc81db0f31f1886dc977fc1ac1ebe6addedf6a59efe2b9802ed4f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discovering governing partial differential equations (PDEs) from observational data remains a core challenge across the sciences. Existing sparse-regression, symbolic-regression, and LLM-based approaches can be constrained by predefined libraries, noise sensitivity, hallucination, or limited iterative refinement. We introduce \textbf{MAGE} (\textbf{M}ultimodal \textbf{A}gentic \textbf{G}overning \textbf{E}quation Discovery), an agentic framework that organizes PDE discovery as a \textit{confidence governed hypothesis validation loop} inspired by the scientific cycle of observation, hypothesis, and falsification. Four role-specialized agents collaborate: a \textit{Differential Observer} computing derivatives and diagnostic visualizations; a VLM-powered \textit{Phenomenology Extractor} distilling qualitative cues from multimodal diagnostics; an LLM-driven \textit{Governing Law Synthesizer} proposing candidates without a predefined library; and an \textit{Equation Arbiter} fitting coefficients and assigning confidence scores. Discovery iterates until the top candidate clears a user-specified threshold, providing a structured process with an explicit accept-reject protocol. On the evaluated canonical PDE suite, MAGE obtains \textbf{8/8} exact structural recovery and the lowest coefficient error among the compared methods on \textbf{7/8} systems, with improvements of up to \textbf{4 orders of magnitude} and a geometric-mean improvement of approximately \textbf{3 orders of magnitude}. The pipeline also recovers the expected operators in two complex geometries and, on one laboratory sensor record, selects a cubic restoring-force model with held-out $R^2=0.98538$. These results support further study of structured agentic reasoning for library-free governing-law discovery, while broader generalization remains to be evaluated.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27869 — 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 2026-10-17T10:33:42.361Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).