ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods

• URL: http://arxiv.org/abs/2603.21011v1
• Date: Thu, 08 Jan 2026 21:25:59 GMT
• Title: ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
• Abstract summary: ALL-FEM is an autonomous simulation system that integrates agentic AI with domain-specific, fine-tuned LLMs for FEniCS code generation.<n>We construct a corpus of 1000+ verified FEniCS scripts by combining curated expert codes with a retrieval-augmented, multi-LLM pipeline.<n>Our agentic framework orchestrates specialized agents, powered by fine-tuned LLMs, to formulate problems as PDEs, generate code and visualize the results.
• Score: 5.727939029920846
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics systems. However, implementing FE codes and analyzing simulation results demands expertise across numerical analysis, continuum mechanics, and programming. Conventional Large Language Models (LLMs) can generate FE code, but they hallucinate, lack awareness of variational structures, and cannot close the loop from problem statement to a verified solution. Here, we propose ALL-FEM, an autonomous simulation system that integrates agentic AI with domain-specific, fine-tuned LLMs for FEniCS code generation across solid, fluid, and multiphysics applications. We construct a corpus of 1000+ verified FEniCS scripts by combining 500+ curated expert codes with a retrieval-augmented, multi-LLM pipeline that generates and filters codes for diverse PDEs, geometries, and boundary conditions. We used the corpus to fine-tune LLMs with 3B to 120B parameters. Our agentic framework orchestrates specialized agents, powered by fine-tuned LLMs, to formulate problems as PDEs, generate and debug code and visualize the results. We evaluated the system on 39 benchmarks that include problems of linear/nonlinear elasticity, plasticity, Newtonian/non-Newtonian flow, thermofluids, fluid-structure interaction, phase separation, and transport on moving domains. Embedded in a multi-agent workflow with runtime feedback, the best fine-tuned model (GPT OSS 120B) achieves code-level success of 71.79%, outperforming a non-agentic deployment of GPT 5 Thinking. By showing that relatively small, fine-tuned LLMs, orchestrated through agentic frameworks, can automate FE workflows, ALL-FEM offers a blueprint for autonomous simulation systems in computational science and engineering.

Related papers

• From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities [103.60384544335072]
  Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence.<n>Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities.<n> Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles.
  arXiv  Detail & Related papers  (2026-08-27T10:52:06Z)
• Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System Models [62.62160094849002]
  RADIANT is an engineering methodology that combines MDE with Multi-Agent Large Language Models.<n>It automatically generates heterogeneous models across engineering phases.<n>It provides exact, automated change-impact analysis.
  arXiv  Detail & Related papers  (2026-07-18T08:50:55Z)
• VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis [34.66954835079288]
  VFEAgent is an end-to-end multi-agent system designed to automate FEA modeling and simulation directly from input images and problem descriptions.<n>VFEAgent achieves a high success rate in generating complete and physically valid simulations.
  arXiv  Detail & Related papers  (2026-05-27T18:34:04Z)
• Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows [2.1149232897113497]
  We propose Lang2MLIP, a multi-agent framework that takes natural-language input and formulates end-to-end MLIP development.<n>At each step, a decision-making agent observes the current dataset, model, evaluation results, and execution log, and then automatically selects an appropriate action to improve the model.<n>We evaluate this approach on a solid electrolyte interphase (SEI) system with multiple components and interfaces.
  arXiv  Detail & Related papers  (2026-05-14T08:10:42Z)
• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations [13.253932177045842]
  Force field-based molecular dynamics (MD) simulations are indispensable for probing the structure, dynamics, and functions of biomolecular systems.<n>The technical complexity of MD setup, encompassing parameterization, input preparation, and software configuration, remains a major barrier for widespread and efficient usage.<n>Here, we present DynaMate, a modular multi-agent framework that autonomously designs and executes complete MD for both protein and protein-ligand systems.
  arXiv  Detail & Related papers  (2025-12-10T19:40:51Z)
• CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation [6.71937346130764]
  CFD-copilot is a framework designed to facilitate natural language-driven CFD simulation from setup to post-processing.<n>For post-processing, the framework utilizes the model context protocol (MCP), an open standard that decouples LLM reasoning from external tool execution.<n>The framework was evaluated on benchmarks including the NACA0012 airfoil and the three-element 30P-30N airfoil.
  arXiv  Detail & Related papers  (2025-12-08T11:42:32Z)
• From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence [150.3696990310269]
  Large language models (LLMs) have transformed automated software development by enabling direct translation of natural language descriptions into functional code.<n>We provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs.<n>We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder)
  arXiv  Detail & Related papers  (2025-11-23T17:09:34Z)
• ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Domain-Specific Structured Reasoning [4.098524616768554]
  ChatCFD is an automated agent system for OpenFOAM simulations.<n>Its four-stage pipeline enables iterative trial-reflection-refinement for intricate setups.<n>ChatCFD shows strong potential as a modular component in MCP-based agent networks for collaborative multi-agent systems.
  arXiv  Detail & Related papers  (2025-05-28T08:43:49Z)
• MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation [1.951051209076837]
  This paper proposes an automated solution framework, MooseAgent, for the multi-physics simulation framework MOOSE.<n>MooseAgent combines large-scale pre-trained language models (LLMs) with a multi-agent system.<n>Results show that MooseAgent can automate the MOOSE simulation process to a certain extent.
  arXiv  Detail & Related papers  (2025-04-11T15:25:50Z)
• MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science [62.96434290874878]
  Current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks.<n>We develop a new framework, named Multi-Modal Scientific Reasoning with Physics Perception and Simulation (MAPS) based on an MLLM.<n>MAPS decomposes expert-level multi-modal reasoning task into physical diagram understanding via a Physical Perception Model (PPM) and reasoning with physical knowledge via a simulator.
  arXiv  Detail & Related papers  (2025-01-18T13:54:00Z)
• FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation [80.63838153351804]
  We introduce FluidLab, a simulation environment with a diverse set of manipulation tasks involving complex fluid dynamics. At the heart of our platform is a fully differentiable physics simulator, providing GPU-accelerated simulations and gradient calculations. We propose several domain-specific optimization schemes coupled with differentiable physics.
  arXiv  Detail & Related papers  (2023-03-04T07:24:22Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)

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.