Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Min-Yi, Zhang, Shengqi, Wu, Liancheng, Zhong, Jinghui, Chen, Shiyi, Ong, Yew-Soon
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.14353
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912967132446720
author Zheng, Min-Yi
Zhang, Shengqi
Wu, Liancheng
Zhong, Jinghui
Chen, Shiyi
Ong, Yew-Soon
author_facet Zheng, Min-Yi
Zhang, Shengqi
Wu, Liancheng
Zhong, Jinghui
Chen, Shiyi
Ong, Yew-Soon
contents Partial differential equations (PDEs) encode fundamental physical laws, yet closed-form analytical solutions for many important equations remain unknown and typically require substantial human insight to derive. Existing numerical, physics-informed, and data-driven approaches approximate solutions from data rather than systematically deriving symbolic expressions directly from governing equations. Here we introduce LawMind, a law-driven symbolic discovery framework that autonomously constructs closed-form solutions from PDEs and their associated conditions without relying on data or supervision. By integrating structured symbolic exploration with physics-constrained evaluation, LawMind progressively assembles valid solution components guided solely by governing laws. Evaluated on 100 benchmark PDEs drawn from two authoritative handbooks, LawMind successfully recovers closed-form analytical solutions for all cases. Beyond known solutions, LawMind further discovers previously unreported closed-form solutions to both linear and nonlinear PDEs. These findings establish a computational paradigm in which governing equations alone drive autonomous symbolic discovery, enabling the systematic derivation of analytical PDE solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14353
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LawMind: A Law-Driven Paradigm for Discovering Analytical Solutions to Partial Differential Equations
Zheng, Min-Yi
Zhang, Shengqi
Wu, Liancheng
Zhong, Jinghui
Chen, Shiyi
Ong, Yew-Soon
Symbolic Computation
Partial differential equations (PDEs) encode fundamental physical laws, yet closed-form analytical solutions for many important equations remain unknown and typically require substantial human insight to derive. Existing numerical, physics-informed, and data-driven approaches approximate solutions from data rather than systematically deriving symbolic expressions directly from governing equations. Here we introduce LawMind, a law-driven symbolic discovery framework that autonomously constructs closed-form solutions from PDEs and their associated conditions without relying on data or supervision. By integrating structured symbolic exploration with physics-constrained evaluation, LawMind progressively assembles valid solution components guided solely by governing laws. Evaluated on 100 benchmark PDEs drawn from two authoritative handbooks, LawMind successfully recovers closed-form analytical solutions for all cases. Beyond known solutions, LawMind further discovers previously unreported closed-form solutions to both linear and nonlinear PDEs. These findings establish a computational paradigm in which governing equations alone drive autonomous symbolic discovery, enabling the systematic derivation of analytical PDE solutions.
title LawMind: A Law-Driven Paradigm for Discovering Analytical Solutions to Partial Differential Equations
topic Symbolic Computation
url https://arxiv.org/abs/2603.14353