AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface Flow

• URL: http://arxiv.org/abs/2604.11945v1
• Date: Mon, 13 Apr 2026 18:36:02 GMT
• Title: AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface Flow
• Abstract summary: AutoSurrogate is a large-language-model-driven multi-agent framework for building deep learning surrogates for subsurface flow problems.<n>It enables practitioners without machine learning expertise to build high-quality surrogates through natural-language instructions.<n>We demonstrate the utility of AutoSurrogate on a 3D geological carbon storage modeling task, mapping permeability fields to pressure and CO$$ saturation fields over 31 timesteps.
• Score: 5.022047193471448
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-fidelity numerical simulation of subsurface flow is computationally intensive, especially for many-query tasks such as uncertainty quantification and data assimilation. Deep learning (DL) surrogates can significantly accelerate forward simulations, yet constructing them requires substantial machine learning (ML) expertise - from architecture design to hyperparameter tuning - that most domain scientists do not possess. Furthermore, the process is predominantly manual and relies heavily on heuristic choices. This expertise gap remains a key barrier to the broader adoption of DL surrogate techniques. For this reason, we present AutoSurrogate, a large-language-model-driven multi-agent framework that enables practitioners without ML expertise to build high-quality surrogates for subsurface flow problems through natural-language instructions. Given simulation data and optional preferences, four specialized agents collaboratively execute data profiling, architecture selection from a model zoo, Bayesian hyperparameter optimization, model training, and quality assessment against user-specified thresholds. The system also handles common failure modes autonomously, including restarting training with adjusted configurations when numerical instabilities occur and switching to alternative architectures when predictive accuracy falls short of targets. In our setting, a single natural-language sentence can be sufficient to produce a deployment-ready surrogate model, with minimum human intervention required at any intermediate stage. We demonstrate the utility of AutoSurrogate on a 3D geological carbon storage modeling task, mapping permeability fields to pressure and CO$_2$ saturation fields over 31 timesteps. Without any manual tuning, AutoSurrogate is able to outperform expert-designed baselines and domain-agnostic AutoML methods, demonstrating strong potential for practical deployment.

Related papers

• 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)
• Surrogate Assisted Pedestrian Protection Design via a Foundation Model Orchestrated Workflow [0.0]
  We present the first foundation model--orchestrated workflow for crash safety design.<n>It enables surrogate-assisted exploration for pedestrian protection, reducing evaluation time from hours per CAE simulation to seconds.<n>In an automotive front-bumper case study, the workflow produces 35 distinct safety-compliant alternatives.
  arXiv  Detail & Related papers  (2026-06-16T06:27:38Z)
• GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis [0.22166578153935787]
  GenAutoML is an agentic framework that leverages Large Language Models as neural architects to bridge natural-language requirements and PyTorch implementations.<n>Experiments on the ETTh1, ETTm1, and Weather benchmarks demonstrate that GenAutoML can dynamically generate task-specific neural architectures tailored to dataset characteristics.<n>By emphasizing computational efficiency, architectural adaptability, and stable optimization behavior, GenAutoML enables the creation of ultra-lightweight neural networks suitable for resource-constrained and latency-sensitive Edge AI deployments.
  arXiv  Detail & Related papers  (2026-06-04T08:35:40Z)
• 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)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models [78.73992315826035]
  We introduce Youtu-LLM, a lightweight language model that harmonizes high computational efficiency with native agentic intelligence.<n>Youtu-LLM is pre-trained from scratch to systematically cultivate reasoning and planning capabilities.
  arXiv  Detail & Related papers  (2025-12-31T04:25:11Z)
• 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)
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model [76.08429266631823]
  We propose an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM)<n>URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction.<n> Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-11-02T13:45:51Z)
• Large Multimodal Models-Empowered Task-Oriented Autonomous Communications: Design Methodology and Implementation Challenges [31.57528074626831]
  Large language models (LLMs) and large multimodal models (LMMs) have achieved unprecedented breakthrough.<n>This article focuses on task-oriented autonomous communications with LLMs/LMMs.<n>We show that the proposed LLM/LMM-aided autonomous systems significantly outperform conventional and discriminative deep learning (DL) model-based techniques.
  arXiv  Detail & Related papers  (2025-10-23T15:08:58Z)
• Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents [3.344730946122235]
  We propose an innovative pipeline utilizing Large Language Model (LLM) agents to automate data-driven modeling and analysis.<n>We evaluate two LLM-agent frameworks: a multi-agent system featuring specialized collaborative agents, and a single-agent system based on the Reasoning and Acting (ReAct) paradigm.
  arXiv  Detail & Related papers  (2025-10-01T19:28:35Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling [71.37579508777843]
  Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities.<n>To address this gap, we present InternBootcamp, an open-source framework comprising 1000+ domain-diverse task environments.
  arXiv  Detail & Related papers  (2025-08-12T05:00:00Z)
• AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs [68.99086112477565]
  Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation.<n>Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads.<n>We propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single- GPU and multi- GPU environments.
  arXiv  Detail & Related papers  (2025-02-27T14:46:22Z)
• Efficient Domain Adaptation of Multimodal Embeddings using Constrastive Learning [0.08192907805418582]
  Current approaches either yield subpar results when using pretrained models without task-specific adaptation, or require substantial computational resources for fine-tuning.<n>We propose a novel method for adapting foundational, multimodal embeddings to downstream tasks, without the need of expensive fine-tuning processes.
  arXiv  Detail & Related papers  (2025-02-04T06:30:12Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Application of an automated machine learning-genetic algorithm (AutoML-GA) coupled with computational fluid dynamics simulations for rapid engine design optimization [0.0]
  The present work describes and validates an automated active learning approach, AutoML-GA, for surrogate-based optimization of internal combustion engines. A genetic algorithm is employed to locate the design optimum on the machine learning surrogate surface. It is demonstrated that AutoML-GA leads to a better optimum with a lower number of CFD simulations.
  arXiv  Detail & Related papers  (2021-01-07T17:50:52Z)

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.