Research

Paper

TESTING March 23, 2026

CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning

Authors

Dongxia Wu, Shiye Su, Yuhui Zhang, Elaine Sui, Emma Lundberg, Emily B. Fox, Serena Yeung-Levy

Abstract

Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the state-of-the-art CellFlux model to yield CellFluxRL. CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling. Overall, our results present a virtual cell modeling framework that enforces physically-based constraints through RL, advancing beyond "visually realistic" generations towards "biologically meaningful" ones.

Metadata

arXiv ID: 2603.21743
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.21743v1</id>\n    <title>CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning</title>\n    <updated>2026-03-23T09:33:18Z</updated>\n    <link href='https://arxiv.org/abs/2603.21743v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.21743v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the state-of-the-art CellFlux model to yield CellFluxRL. CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling. Overall, our results present a virtual cell modeling framework that enforces physically-based constraints through RL, advancing beyond \"visually realistic\" generations towards \"biologically meaningful\" ones.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='q-bio.QM'/>\n    <published>2026-03-23T09:33:18Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Dongxia Wu</name>\n    </author>\n    <author>\n      <name>Shiye Su</name>\n    </author>\n    <author>\n      <name>Yuhui Zhang</name>\n    </author>\n    <author>\n      <name>Elaine Sui</name>\n    </author>\n    <author>\n      <name>Emma Lundberg</name>\n    </author>\n    <author>\n      <name>Emily B. Fox</name>\n    </author>\n    <author>\n      <name>Serena Yeung-Levy</name>\n    </author>\n  </entry>"
}