Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
About
Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimizer refines equations for accuracy, and a Scientist Agent leverages an LLM to conduct both qualitative and quantitative evaluations and synthesize their results to iteratively guide the search. Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations. Our code is available at https://github.com/Bon99yun/DoLQ.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Symbolic Discovery of Ordinary Differential Equations | SIR(2D) ID | Residual NMSE1.71e-8 | 10 | |
| Symbolic Discovery of Ordinary Differential Equations | SIR 2D ID-Ext | Residual NMSE3.98e-9 | 8 | |
| ODE Discovery (Numerical Convergence) | ODE Discovery Benchmark Suite Problems P1-P8 | Total Success Count7 | 5 | |
| ODE Discovery (Structural Recovery) | ODE Discovery Benchmark Suite Problems P1-P8 | Total Structural Recovery Count5 | 5 | |
| Symbolic Discovery of Ordinary Differential Equations | Glider 4D ID | Residual NMSE1.22e-6 | 5 | |
| ODE discovery | ODE Discovery Problem 1 | Found Components (K) In-set20.2 | 5 | |
| ODE discovery | ODE Discovery Problem 3 | Found Components (K) In-set188 | 5 | |
| ODE discovery | ODE Discovery Problem 4 | Components Found (K) In-Sample44.6 | 5 | |
| ODE discovery | ODE Discovery Problem 5 | Found Components (K) In20.4 | 5 | |
| ODE discovery | ODE Discovery Problem 6 | Found Components (In)10.3 | 5 |