Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language

• URL: http://arxiv.org/abs/2608.04384v1
• Date: Wed, 05 Aug 2026 02:41:23 GMT
• Title: Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
• Abstract summary: ADSL-PDE is a search-space representation for neural PDE solver auto-design.<n>It represents the functional decisions that determine a neural PDE solver.<n>A deterministic compiler maps each valid search state to an executable solver.
• Score: 8.10360511033952
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows [72.9051182568928]
  We present ReASearch, a unified framework for reasoning-driven optimization.<n>With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML.<n>We observe that complex search behaviors emerge naturally from the agent's reasoning process.
  arXiv  Detail & Related papers  (2026-08-07T02:15:39Z)
• Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design [10.706452586705375]
  Physics-informed neural networks (PINNs) are sensitive to interacting choices of architecture, activation, loss weighting, collocation, optimization, and constraint enforcement.<n>Large language models (LLMs) can propose these choices, but independent recommendations do not accumulate experience from previously trained PINNs.<n>We propose a closed-loop evolutionary algorithm that guides an LLM to generate complete, executable PINN configurations across generations.
  arXiv  Detail & Related papers  (2026-07-17T02:03:11Z)
• AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies [13.63605095777436]
  We propose AutoPDE, a code agent that maintains the solver strategy as an explicitly represented object throughout the solving process.<n>AutoPDE builds and maintains this object in three stages, all drawing from a library of reusable PDE-solving skills.<n>Experiments show that AutoPDE achieves a pass rate of $54.5%$, improving over the strongest baseline by $14.2$ percentage points.
  arXiv  Detail & Related papers  (2026-06-09T12:02:58Z)
• Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces [63.82675722580452]
  OPT* is a family of optimization-style tasks for training and evaluating LLM step-by-step optimization-like reasoning.<n>Each task provides a feasibility checker and evaluator, while a complexity parameter expands the search space without requiring new human labels.<n>We show that training on OPT* improves step-by-step optimization-like reasoning.
  arXiv  Detail & Related papers  (2026-06-03T21:43:38Z)
• Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework [54.447408954009454]
  Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs)<n>We present Lang-PINN, an LLM-driven multi-agent system that builds trainable PINNs directly from natural language task descriptions.<n>Experiments show that Lang-PINN achieves substantially lower errors and greater robustness than competitive baselines.
  arXiv  Detail & Related papers  (2025-10-03T08:20:02Z)
• 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)
• Quality-Diversity Algorithms Can Provably Be Helpful for Optimization [24.694984679399315]
  Quality-Diversity (QD) algorithms aim to find a set of high-performing, yet diverse solutions. This paper tries to shed some light on the optimization ability of QD algorithms via rigorous running time analysis.
  arXiv  Detail & Related papers  (2024-01-19T07:40:24Z)
• Efficient Quality-Diversity Optimization through Diverse Quality Species [3.428706362109921]
  We show that a diverse population of solutions can be found without the limitation of needing an archive or defining the range of behaviors in advance. We propose Diverse Quality Species (DQS) as an alternative to archive-based Quality-Diversity (QD) algorithms.
  arXiv  Detail & Related papers  (2023-04-14T23:15:51Z)
• Learning To Dive In Branch And Bound [95.13209326119153]
  We propose L2Dive to learn specific diving structurals with graph neural networks. We train generative models to predict variable assignments and leverage the duality of linear programs to make diving decisions.
  arXiv  Detail & Related papers  (2023-01-24T12:01:45Z)
• Message Passing Neural PDE Solvers [60.77761603258397]
  We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
  arXiv  Detail & Related papers  (2022-02-07T17:47:46Z)
• dNNsolve: an efficient NN-based PDE solver [62.997667081978825]
  We introduce dNNsolve, that makes use of dual Neural Networks to solve ODEs/PDEs. We show that dNNsolve is capable of solving a broad range of ODEs/PDEs in 1, 2 and 3 spacetime dimensions.
  arXiv  Detail & Related papers  (2021-03-15T19:14:41Z)

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.