Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
Sum Kyun Song, Bong Gyun Shin, Jae Yong Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the Scientist Agent (qualitative plus quantitative term evaluation) (ablation) | DoLQ · Glider(2D) | iterations to find correct equation: 62 -> 27 | Improved |
| use DoLQ instead of LLM-SR | DoLQ · CDIMA(2D) integral NMSE ID | NMSE: 3.14e-3 -> 2.35e-8 | Improved |
| use DoLQ instead of LLM-SR | DoLQ · CDIMA(2D) integral NMSE ID-Ext | NMSE: 9.38e-3 -> 1.15e-7 | Improved |
| use DoLQ instead of LLM-SR | DoLQ · Glider(4D) integral NMSE ID | NMSE: 8.54e-7 -> 8.29e-7 | No clear effect |
| use DoLQ instead of LLM-SR | DoLQ · Glider(4D) integral NMSE ID-Ext | NMSE: 4.76e-6 -> 5.21e-6 | No clear effect |
| use DoLQ instead of ICSR | DoLQ · SIR(2D) integral NMSE ID | NMSE: 1.42e-8 -> 1.55e-8 | No clear effect |
| use DoLQ instead of L SR | DoLQ · SIR(2D) integral NMSE ID | NMSE: 7.60e-9 -> 1.55e-8 | No clear effect |
| use DoLQ instead of ICSR | DoLQ · CDIMA(2D) integral NMSE ID | NMSE: 3.78e-4 -> 2.35e-8 | Improved |
| add hybrid differential evolution plus BFGS optimization instead of BFGS alone (ablation) | DoLQ · parameter fitting with correct skeleton | parameter recovery | Improved |
| add the Scientist Agent's term filtering | DoLQ · 8 ODE benchmarks | equation size and token usage | Improved |
Closest papers by meaning
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models (ICLR 2025 · similarity 0.88)
- LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models (ICML 2025 · similarity 0.87)
- Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching (AAAI 2025 · similarity 0.86)
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers (ICLR 2024 · similarity 0.85)
- Symmetry-Informed Governing Equation Discovery (NeurIPS 2024 · similarity 0.85)
- No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
