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
It outperforms existing methods by integrating domain knowledge and mechanistic constraints, demonstrating effective retrieval and extrapolation capabilities.
Key Points
- MEDA integrates symbolic regression and 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.
DeepSignal Analysis
What happened
The MEDA system has been developed to autonomously discover ordinary differential equations (ODEs) for biological systems using large language models and symbolic regression. It demonstrates strong performance in retrieving and extrapolating models, achieving biologically plausible results. The system integrates domain knowledge and mechanistic constraints, which are crucial for its effectiveness.
Key evidence
- The MEDA system utilizes large language models and symbolic regression to discover ODE models for biological systems.
- MEDA achieved strong structural recovery in retrieval and extrapolation tasks, producing biologically plausible models.
- Ablation analyses indicate that knowledge-guided formalization and mechanistic constraints are essential components of the MEDA system.
Why it matters
This advancement in automatic scientific discovery could significantly enhance the modeling of complex biological systems, moving beyond traditional data-fitting methods. By integrating domain knowledge, MEDA may lead to more accurate and relevant models that can inform biological research and applications. The implications for fields such as systems biology and computational biology could be profound, potentially accelerating discoveries and innovations.
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 →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.