PDE-SHARP: PDE Solver Hybrids through Analysis and Refinement Passes

• URL: http://arxiv.org/abs/2511.00183v2
• Date: Wed, 05 Nov 2025 17:58:32 GMT
• Title: PDE-SHARP: PDE Solver Hybrids through Analysis and Refinement Passes
• Authors: Shaghayegh Fazliani, Madeleine Udell,
• Abstract summary: We introduce PDE-SHARP, a framework to reduce computational costs by replacing expensive scientific computation by cheaper LLM inference.<n>PDE-SHARP achieves superior solver accuracy with 60-75% fewer computational evaluations.<n>To generate high-quality solvers, PDE-SHARP requires fewer than 13 solver evaluations on average compared to 30+ for baseline methods.
• Score: 12.096472648029204
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current LLM-driven approaches using test-time computing to generate PDE solvers execute a large number of solver samples to identify high-accuracy solvers. These paradigms are especially costly for complex PDEs requiring substantial computational resources for numerical evaluation. We introduce PDE-SHARP, a framework to reduce computational costs by replacing expensive scientific computation by cheaper LLM inference that achieves superior solver accuracy with 60-75% fewer computational evaluations. PDE-SHARP employs three stages: (1) Analysis: mathematical chain-of-thought analysis including PDE classification, solution type detection, and stability analysis; (2) Genesis: solver generation based on mathematical insights from the previous stage; and (3) Synthesis: collaborative selection-hybridization tournaments in which LLM judges iteratively refine implementations through flexible performance feedback. To generate high-quality solvers, PDE-SHARP requires fewer than 13 solver evaluations on average compared to 30+ for baseline methods, improving accuracy uniformly across tested PDEs by $4\times$ on average, and demonstrates robust performance across LLM architectures, from general-purpose to specialized reasoning models.

Related papers

• Neuro-Symbolic Multitasking: A Unified Framework for Discovering Generalizable Solutions to PDE Families [7.3387140039389385]
  Partial Differential Equations (PDEs) are fundamental to numerous scientific and engineering disciplines.<n>Traditional numerical methods, such as the finite element method, need to independently solve each instance within a PDE family.<n>We propose a neuro-assisted multitasking symbolic PDE solver framework for PDE family solving, dubbed NMIPS.
  arXiv  Detail & Related papers  (2026-02-12T06:25:44Z)
• PDE-Agent: A toolchain-augmented multi-agent framework for PDE solving [50.54386756067269]
  Solving Partial Differential Equations (PDEs) is a cornerstone of engineering and scientific research.<n>Traditional methods for PDE solving are cumbersome, relying on manual setup and domain expertise.<n>In this work, we frame PDE solving as tool invocation via LLM-driven agents.<n>We introduce PDE-Agent, the first toolchain-augmented multi-agent collaboration framework.
  arXiv  Detail & Related papers  (2025-12-18T06:02:50Z)
• High precision PINNs in unbounded domains: application to singularity formulation in PDEs [83.50980325611066]
  We study the choices of neural network ansatz, sampling strategy, and optimization algorithm.<n>For 1D Burgers equation, our framework can lead to a solution with very high precision.<n>For the 2D Boussinesq equation, we obtain a solution whose loss is $4$ digits smaller than that obtained in citewang2023asymptotic with fewer training steps.
  arXiv  Detail & Related papers  (2025-06-24T02:01:44Z)
• CodePDE: An Inference Framework for LLM-driven PDE Solver Generation [57.15474515982337]
  Partial differential equations (PDEs) are fundamental to modeling physical systems.<n>Traditional numerical solvers rely on expert knowledge to implement and are computationally expensive.<n>We introduce CodePDE, the first inference framework for generating PDE solvers using large language models.
  arXiv  Detail & Related papers  (2025-05-13T17:58:08Z)
• Paving the way for scientific foundation models: enhancing generalization and robustness in PDEs with constraint-aware pre-training [49.8035317670223]
  A scientific foundation model (SciFM) is emerging as a promising tool for learning transferable representations across diverse domains.<n>We propose incorporating PDE residuals into pre-training either as the sole learning signal or in combination with data loss to compensate for limited or infeasible training data.<n>Our results show that pre-training with PDE constraints significantly enhances generalization, outperforming models trained solely on solution data.
  arXiv  Detail & Related papers  (2025-03-24T19:12:39Z)
• Active Learning for Neural PDE Solvers [18.665448858377694]
  Active learning could help surrogate models reach the same accuracy with smaller training sets.<n>We introduce AL4PDE, a modular and active learning benchmark.<n>We show that AL reduces the average error by up to 71% compared to random sampling.
  arXiv  Detail & Related papers  (2024-08-02T18:48:58Z)
• Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers [53.79279286773326]
  We present Unisolver, a novel Transformer model trained on diverse data and conditioned on diverse PDEs.<n>Unisolver achieves consistent state-of-the-art on three challenging large-scale benchmarks, showing impressive performance and generalizability.
  arXiv  Detail & Related papers  (2024-05-27T15:34:35Z)
• A composable autoencoder-based iterative algorithm for accelerating numerical simulations [0.0]
  CoAE-MLSim is an unsupervised, lower-dimensional, local method that is motivated from key ideas used in commercial PDE solvers. It is tested for a variety of complex engineering cases to demonstrate its computational speed, accuracy, scalability, and generalization across different PDE conditions.
  arXiv  Detail & Related papers  (2021-10-07T20:22:37Z)
• Solving Multistage Stochastic Linear Programming via Regularized Linear Decision Rules: An Application to Hydrothermal Dispatch Planning [77.34726150561087]
  We propose a novel regularization scheme for linear decision rules (LDR) based on the AdaSO (adaptive least absolute shrinkage and selection operator) Experiments show that the overfit threat is non-negligible when using the classical non-regularized LDR to solve MSLP. For the LHDP problem, our analysis highlights the following benefits of the proposed framework in comparison to the non-regularized benchmark.
  arXiv  Detail & Related papers  (2021-10-07T02:36:14Z)
• DiscretizationNet: A Machine-Learning based solver for Navier-Stokes Equations using Finite Volume Discretization [0.7366405857677226]
  The goal of this work is to develop an ML-based PDE solver, that couples important characteristics of existing PDE solvers with Machine Learning technologies. Our ML-solver, DiscretizationNet, employs a generative CNN-based encoder-decoder model with PDE variables as both input and output features. A novel iterative capability is implemented during the network training to improve the stability and convergence of the ML-solver.
  arXiv  Detail & Related papers  (2020-05-17T19:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.