Automated model discovery is the process of automatically searching and identifying the most appropriate model for a given dataset over a large combinatorial search space. Existing approaches, however, often face challenges in balancing the capture of fine-grained details with ensuring generalizability beyond training data regimes with a reasonable model complexity. In this paper, we present a multi-modal & multi-step pipeline for effective automated model discovery. Our approach leverages two vision-language-based modules (VLM), AnalyzerVLM and EvaluatorVLM, for effective model proposal and evaluation in an agentic way. AnalyzerVLM autonomously plans and executes multi-step analyses to propose effective candidate models. EvaluatorVLM assesses the candidate models both quantitatively and perceptually, regarding the fitness for local details and the generalibility for overall trends. Our results demonstrate that our pipeline effectively discovers models that capture fine details and ensure strong generalizability. Additionally, extensive ablation studies show that both multi-modality and multi-step reasoning play crucial roles in discovering favorable models.
At Gaussian Process Kernel Discovery, our pipeline can effectively search for the kernel composition compared to previous pipelines.
Using Symbolic Regression, our pipeline also can work as effective symbolic regressor, searching for the appropriate function composition.
@inproceedings{
jung-mok2025automated,
title={Automated Model Discovery via Multi-modal \& Multi-step Pipeline},
author={Lee Jung-Mok and Nam Hyeon-Woo and Moon Ye-Bin and Junhyun Nam and Tae-Hyun Oh},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=qGFvTIMS3W}
}