mlsanityData to 14 Oct 2026

Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks

arXiv 2505.07956 ↗First posted 12 May 2025cs.LG cs.NE cs.SCcited by 3

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a univariate function and tasked with proposing an ansatz for that function. The free parameters of the ansatz are fitted using standard numerical optimisers, and a collection of such ans"atze make up the population of a genetic algorithm. Unlike other symbolic regression techniques, our method does not require the specification of a set of functions to be used in regression, but with appropriate prompt engineering, we can arbitrarily condition the generative step. By using Kolmogorov Arnold Networks (KANs), we demonstrate that ``univariate is all you need'' for symbolic regression, and extend this method to multivariate functions by learning the univariate function on each edge of a trained KAN. The combined expression is then simplified by further processing with a language model.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 11 of its 19 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

11 of 19 references.

References · 11

  1. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  2. 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 548
  3. 2021Contemporary Symbolic Regression Methods and their Relative Performancecited by 215
  4. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 133
  5. 2024Symbolic Regression with a Learned Concept Librarycited by 83
  6. 2023Interpretable Machine Learning for Science with PySR and SymbolicRegression.jlcited by 54
  7. 2024In-Context Symbolic Regression: Leveraging Large Language Models for Function Discoverycited by 31
  8. 2022Exhaustive Symbolic Regressioncited by 29
  9. 2024TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMscited by 24
  10. 2025Generative Modeling for Mathematical Discoverycited by 10
  11. 2025Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SINDy-KANs: Sparse identification of non-linear dynamics through Kolmogorov-Arnold networkscited by 3
  2. 2026DeepInflation: an AI agent for research and model discovery of inflationcited by 1
  3. 2026From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Datacited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
  2. 2024Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens
  3. 2026Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models
  4. 2024Large Language Models are Interpretable Learners
  5. 2024MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task
  6. 2024In Context Learning and Reasoning for Symbolic Regression with Large Language Models
  7. 2025Iterated Agent for Symbolic Regression
  8. 2024Neuro-Symbolic Data Generation for Math Reasoning