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

arXiv: https://arxiv.org/abs/2505.02766 · HTML: https://mlsanity.com/paper/2505.02766/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 5 May 2025.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Surpassing Cosine Similarity for Multidimensional Comparisons: Dimension Insensitive Euclidean Metric](https://mlsanity.com/paper/2407.08623/) (2024)
- [Emergent Collective Reproduction via Evolving Neuronal Flocks](https://mlsanity.com/paper/2409.13254/) (2024)

## Built on by (most cited first, 2 of 2)

- [ZapGPT: Free-form Language Prompting for Simulated Cellular Control](https://mlsanity.com/paper/2509.10660/) (2025)
- [Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots](https://mlsanity.com/paper/2610.02247/) (2026)

## Abstract (arXiv)

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.