Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
Quick Answer
This paper shows that The MEDA system utilizes large language models and symbolic regression to autonomously discover ordinary differential equations for biological systems, achieving strong structural recovery and biologically plausible models.
Quick Take
The MEDA system utilizes large language models and symbolic regression to autonomously discover ordinary differential equations for biological systems, achieving strong structural recovery and biologically plausible models. It outperforms existing methods by integrating domain knowledge and mechanistic constraints, demonstrating effective retrieval and extrapolation capabilities.
Key Points
- MEDA integrates symbolic regression and LLMs for ODE discovery in biological systems.
- It successfully retrieves correct state variables and achieves strong structural recovery.
- The system generates biologically plausible models with and without experimental data.
- Knowledge-guided formalization is crucial for accurate model discovery.
- Numerical fitting alone may yield biologically incorrect equations despite trajectory compatibility.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.
| Subjects: | Artificial Intelligence (cs.AI); Dynamical Systems (math.DS) |
| Cite as: | arXiv:2607.13608 [cs.AI] |
| (or arXiv:2607.13608v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.13608 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Teddy Lazebnik Prof. [view email]
[v1]
Wed, 15 Jul 2026 08:56:56 UTC (105 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning
The paper introduces Geospatial Foundation Models (GeoFMs), AI/ML models pre-trained on extensive geospatial datasets, enabling domain experts to fine-tune them for specific tasks. This paradigm shift democratizes access to advanced AI/ML while ensuring security, and proposes a framework for cost-effective adaptation strategies. The vision of Agentic Geospatial Reasoning is also presented, where Large Language Models orchestrate GeoFMs to automate complex analytical workflows.