GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis

• URL: http://arxiv.org/abs/2606.05860v2
• Date: Thu, 11 Jun 2026 12:39:42 GMT
• Title: GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis
• Abstract summary: 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.
• Score: 0.22166578153935787
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing neural architectures for time-series forecasting and anomaly detection remains a resource-intensive task that often requires substantial domain expertise. Traditional Automated Machine Learning (AutoML) systems typically rely on static, predefined search spaces, limiting their ability to adapt to diverse data characteristics. We present GenAutoML, an agentic framework that leverages Large Language Models (LLMs) as neural architects to bridge natural-language requirements and executable PyTorch implementations. The framework incorporates a Sandboxed Reflection Loop for autonomous code refinement and a Signature-Aware Runtime that enforces architectural consistency and execution safety. To improve robustness under non-stationary conditions, we further introduce a Dynamic Reversible Instance Normalization (Dyn-RevIN) wrapper. Experiments on the ETTh1, ETTm1, and Weather benchmarks demonstrate that GenAutoML can dynamically generate task-specific neural architectures tailored to dataset characteristics. Among the generated models, WaveInterferenceNet achieves inference latency below 0.01 ms per sample while maintaining competitive predictive performance. 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.

Related papers

• AutoRAS: Learning Robust Agentic Systems with Primitive Representations [24.053606410215128]
  AutoRAS is a framework for the automated design of robust agentic systems.<n>Experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings.
  arXiv  Detail & Related papers  (2026-06-19T14:05:37Z)
• OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models [69.2503510410147]
  We present a unified autonomous driving framework built upon a pretrained VLM.<n>We demonstrate that pretrained VLM attention exhibits strong transferability beyond pure language modeling.<n>Experiments on end-to-end autonomous driving benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-20T07:50:00Z)
• AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface Flow [5.022047193471448]
  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.
  arXiv  Detail & Related papers  (2026-04-13T18:36:02Z)
• Towards a Self-Driving Trigger at the LHC: Adaptive Response in Real Time [8.632121079404772]
  Real-time data filtering and selection must process extremely high-rate data streams.<n>These systems are typically designed as static, hand-tuned menus of selection criteria.<n>We explore the concept of a self-driving trigger that reallocates resources and adjusts thresholds dynamically in real-time.
  arXiv  Detail & Related papers  (2026-01-13T19:00:02Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• LEMUR Neural Network Dataset: Towards Seamless AutoML [35.57280723615144]
  We introduce LEMUR, an open-source dataset and framework that provides a large collection of PyTorch-based neural networks.<n>Each model follows a unified template, with configurations and results stored in a structured database to ensure consistency.<n>LEMUR aims to accelerate AutoML research, enable fair benchmarking, and reduce barriers to large-scale neural network research.
  arXiv  Detail & Related papers  (2025-04-14T09:08:00Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• auto-sktime: Automated Time Series Forecasting [18.640815949661903]
  We introduce auto-sktime, a novel framework for automated time series forecasting. The proposed framework uses the power of automated machine learning (AutoML) techniques to automate the creation of the entire forecasting pipeline. Experimental results on 64 diverse real-world time series datasets demonstrate the effectiveness and efficiency of the framework.
  arXiv  Detail & Related papers  (2023-12-13T21:34:30Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)
• Resource-Aware Pareto-Optimal Automated Machine Learning Platform [1.6746303554275583]
  novel platform Resource-Aware AutoML (RA-AutoML) RA-AutoML enables flexible and generalized algorithms to build machine learning models subjected to multiple objectives.
  arXiv  Detail & Related papers  (2020-10-30T19:37:48Z)
• Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL [53.40030379661183]
  Auto-PyTorch is a framework to enable fully automated deep learning (AutoDL) It combines multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) We show that Auto-PyTorch performs better than several state-of-the-art competitors on average.
  arXiv  Detail & Related papers  (2020-06-24T15:15:17Z)

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.