Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control

TL;DR

This paper introduces a novel pipeline that uses large language models and evolutionary strategies to translate natural language prompts into control signals for directing simulated cellular behaviors, bridging AI language understanding and biological system control.

Contribution

It presents the first functional system combining language models with evolvable neural controllers to steer cellular simulations based on plain language instructions.

Findings

Evolved models successfully control simulated cell behaviors like clustering and scattering.

The system works with limited vocabulary and simplified cell models.

Provides a complete language-to-behavior control loop for cellular systems.

Abstract

Guiding biological systems toward desired states, such as morphogenetic outcomes, remains a fundamental challenge with far-reaching implications for medicine and synthetic biology. While large language models (LLMs) have enabled natural language as an interface for interpretable control in AI systems, their use as mediators for steering biological or cellular dynamics remains largely unexplored. In this work, we present a functional pipeline that translates natural language prompts into spatial vector fields capable of directing simulated cellular collectives. Our approach combines a large language model with an evolvable neural controller (Prompt-to-Intervention, or P2I), optimized via evolutionary strategies to generate behaviors such as clustering or scattering in a simulated 2D environment. We demonstrate that even with constrained vocabulary and simplified cell models, evolved P2I networks can successfully align cellular dynamics with user-defined goals expressed in plain language. This work offers a complete loop from language input to simulated bioelectric-like intervention to behavioral output, providing a foundation for future systems capable of natural language-driven cellular control.