Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System

Source

arXiv

arxiv.org/abs/2607.13608v1

Read the source

Source

Plain-Language Brief

The MEDA system is a new framework that uses large language models and symbolic regression to automatically discover ordinary differential equation (ODE) models for biological systems. The system retrieves background knowledge, defines variables, generates constraints, proposes candidate ODEs, fits them, and evaluates them. The authors evaluate the MEDA system across different tasks and show that it can recover the correct state variables, achieve strong structural recovery in retrieval and extrapolation tasks, and produce biologically plausible discovery-oriented models.

What the Document Says

  • MEDA is an LLM and SR powered agentic framework for discovering ODE models of biological systems.
  • MEDA retrieves background knowledge and defines variables.
  • MEDA generates mechanistic constraints, proposes candidate ODEs, fits them, and evaluates them.
  • The authors evaluate MEDA across different tasks including canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery.
  • MEDA can recover the correct state variables, achieve strong structural recovery in retrieval and extrapolation tasks, and produce biologically plausible discovery-oriented models.
  • Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components. Numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.

Key Concepts Mentioned

  • MEDA system
  • Ordinary Differential Equations (ODE)
  • Biological Systems
  • Large Language Model (LLM)
  • Symbolic Regression (SR)
  • Background Knowledge
  • State Variables
  • Mechanistic Constraints
  • Canonical Model Retrieval
  • Reasoning-Based Extrapolation
  • Open-Ended Discovery

Claims Made by the Document

  • MEDA can discover ODE models for biological systems.
  • MEDA can recover the correct state variables.
  • MEDA can achieve strong structural recovery in retrieval and extrapolation tasks.

Evidence Used

  • The text describes how MEDA retrieves, defines, generates, proposes, fits, evaluates ODE models for biological systems.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.