mlsanityData to 7 Oct 2026

Large language models for partial differential equation workflows

arXiv 2608.03600 ↗First posted 4 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Numerical methods and deep learning have advanced the modelling and simulation of systems governed by partial differential equations (PDEs), while formulating equations, configuring solvers, and translating simulations into design and control decisions continue to demand substantial domain expertise and computational resources. Large language models (LLMs) offer opportunities to automate and coordinate these tasks by combining scientific knowledge, mathematical reasoning, code generation, and tool use. Here we review LLM-assisted PDE research across three stages, including discovery, solving, and optimization. We examine how LLMs interact with physical knowledge, numerical methods, and computational feedback to formulate models, implement solution procedures, and guide design and control. We also review existing benchmarks and evaluation practices for assessing scientific validity, computational performance, and workflow reliability. Finally, we discuss three interconnected challenges and opportunities: developing mathematical and physical reasoning tailored to specific PDE problems; building transferable domain expertise through domain-specific and multimodal post-training; and integrating active experimental design with scientific validation for open-ended problems. These directions outline a path towards a more substantive role for LLMs in developing and testing scientific ideas and computational methods across PDE research.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 91 of its 185 references that are in the map. First posted on arXiv 4 Aug 2026.

Builds on

91 of 185 references.

References · 91

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  5. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  6. 2017Solving high-dimensional partial differential equations using deep learningcited by 549
  7. 2021Machine learning accelerated computational fluid dynamicscited by 461
  8. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 396
  9. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  10. 2021Physics-informed neural networks with hard constraints for inverse designcited by 277
  11. 2021Factorized Fourier Neural Operatorscited by 237
  12. 2021Gradient-enhanced physics-informed neural networks for forward and inverse PDE problemscited by 220
38 more
  1. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discoverycited by 208
  2. 2024SciCode: A Research Coding Benchmark Curated by Scientistscited by 172
  3. 2020Physics-informed learning of governing equations from scarce datacited by 167
  4. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  5. 2026Towards End-to-End Automation of AI Researchcited by 150
  6. 2020Learning to Control PDEs with Differentiable Physicscited by 131
  7. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  8. 2023The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4cited by 112
  9. 2023PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEscited by 84
  10. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 82
  11. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  12. 2024DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarkscited by 74
  13. 2023MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledgecited by 62
  14. 2021Encoding physics to learn reaction-diffusion processescited by 61
  15. 2025LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Modelscited by 61
  16. 2024LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languagescited by 46
  17. 2024Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolationcited by 45
  18. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFDcited by 39
  19. 2025CodePDE: An Inference Framework for LLM-driven PDE Solver Generationcited by 37
  20. 2024DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamicscited by 33
  21. 2024Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solverscited by 31
  22. 2025SR-Scientist: Scientific Equation Discovery With Agentic AIcited by 30
  23. 2019Direct shape optimization through deep reinforcement learningcited by 28
  24. 2024UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptationcited by 27
  25. 2023ChatGPT for Programming Numerical Methodscited by 26
  26. 2024Text2PDE: Latent Diffusion Models for Accessible Physics Simulationcited by 25
  27. 2024Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Contextcited by 25
  28. 2025MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problemcited by 24
  29. 2025PDE-Controller: LLMs for Autoformalization and Reasoning of PDEscited by 23
  30. 2023Physics Informed Token Transformer for Solving Partial Differential Equationscited by 21
  31. 2025FEABench: Evaluating Language Models on Multiphysics Reasoning Abilitycited by 21
  32. 2025DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experiencecited by 20
  33. 2025Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulationscited by 18
  34. 2025PINNsAgent: Automated PDE Surrogation with Large Language Modelscited by 17
  35. 2020Data-Driven Discovery of Coarse-Grained Equationscited by 14
  36. 2024LLM4ED: Large Language Models for Automatic Equation Discoverycited by 13
  37. 2025MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processingcited by 13
  38. 2025AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learningcited by 13

50 most cited of 91 All 91 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithm
  2. 2026Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards
  3. 2026AutoPDEBench: Benchmarking LLM Auto-Research for Neural PDE Solver Design
  4. 2025Towards a Foundation Model for Partial Differential Equations Across Physics Domains
  5. 2025Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
  6. 2023Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models
  7. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
  8. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers