DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery
Roberto Aliaga Medina, Paulina Quintanilla, Antonio del Rio Chanona
cs.LG, cs.CE, cs.SC
Submitted: 2026-08-05
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Kinetic model discovery is a central challenge in chemical engineering, as accurate rate expressions are essential for understanding and controlling chemical and biological processes.
Terminology
Abstract
Kinetic model discovery is a central challenge in chemical engineering, as accurate rate expressions are essential for understanding and controlling chemical and biological processes. Symbolic regression (SR) has emerged as a powerful data-driven approach for identifying interpretable kinetic models, but usually operates without domain knowledge, often exploring physicochemically implausible models. Large language models (LLMs) offer a promising avenue for injecting domain expertise into this search. Here, we introduce an LLM-guided SR framework, embedding an LLM module within an iterative SR algorithm for automated kinetic model discovery. The LLM performs two roles at each iteration: (1) a qualitative physicochemical critique of the best SR candidates, and (2) the proposal of new candidate rate expressions guided by the SR-generated models and embedded chemical knowledge. Our framework is evaluated on four in silico case studies of increasing complexity, spanning heterogeneous catalysis and bioprocess systems. Results show the LLM-guided framework reduces iterations to identify the ground-truth model by 41.7-79.3% versus a state-of-the-art SR framework, with the LLM directly proposing the correct model structure in over half of the guided runs. In practical settings, where each iteration typically requires a new wet-lab experiment, this translates into a substantial reduction in experimental effort. Predictive performance on an independent validation set is equivalent between both approaches, with R 2>0.98 in all case studies. Ablation studies indicate that both the SR component and the LLM scale contribute to this performance, with a reduced-size LLM largely retaining discovery efficiency. These findings demonstrate that LLMs can effectively inject domain knowledge into scientific model discovery, paving the way toward fully automated, domain-aware kinetic modelling pipelines.
Sources
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- Symbolic Discovery of Stochastic Differential Equations with Genetic Programming
- LLM-ODE: Data-driven Discovery of Dynamical Systems with Large Language Models
- LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression
- Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
- Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
- LLM4ED: Large Language Models for Automatic Equation Discovery
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
- LLM-DMD: Large Language Model-based Power System Dynamic Model Discovery
- A Probabilistic Framework for LLM-Based Model Discovery
- Symbolic Regression with a Learned Concept Library
- Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
- Qwen3 Technical Report
- Physics-Informed Regression: Parameter Estimation in Parameter-Linear Nonlinear Dynamic Models
- Population-based Optimization for Kinetic Parameter Identification in Glycolytic Pathway in Saccharomyces cerevisiae
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks