Saved in:
Bibliographic Details
Main Authors: Jang, Yunhui, Zhu, Lu, Fawkes, Jake, Denton, Alisandra Kaye, Beaini, Dominique, Noutahi, Emmanuel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11661
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916031633555456
author Jang, Yunhui
Zhu, Lu
Fawkes, Jake
Denton, Alisandra Kaye
Beaini, Dominique
Noutahi, Emmanuel
author_facet Jang, Yunhui
Zhu, Lu
Fawkes, Jake
Denton, Alisandra Kaye
Beaini, Dominique
Noutahi, Emmanuel
contents Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, primarily due to the lack of factually grounded and actionable explanations. To address this, we introduce a structured explanation formalism for virtual cells that represents biological reasoning as mechanistic action graphs, enabling systematic verification and falsification. Building upon this, we propose VCR-Agent, a multi-agent framework that integrates biologically grounded knowledge retrieval with a verifier-based filtering approach to generate and validate mechanistic reasoning autonomously. Using this framework, we release VC-TRACES dataset, which consists of verified mechanistic explanations derived from the Tahoe-100M atlas. Empirically, we demonstrate that training with these explanations improves factual precision and provides a more effective supervision signal for downstream gene expression prediction. These results underscore the importance of reliable mechanistic reasoning for virtual cells, achieved through the synergy of multi-agent and rigorous verification.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11661
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Autonomous Mechanistic Reasoning in Virtual Cells
Jang, Yunhui
Zhu, Lu
Fawkes, Jake
Denton, Alisandra Kaye
Beaini, Dominique
Noutahi, Emmanuel
Machine Learning
Artificial Intelligence
Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, primarily due to the lack of factually grounded and actionable explanations. To address this, we introduce a structured explanation formalism for virtual cells that represents biological reasoning as mechanistic action graphs, enabling systematic verification and falsification. Building upon this, we propose VCR-Agent, a multi-agent framework that integrates biologically grounded knowledge retrieval with a verifier-based filtering approach to generate and validate mechanistic reasoning autonomously. Using this framework, we release VC-TRACES dataset, which consists of verified mechanistic explanations derived from the Tahoe-100M atlas. Empirically, we demonstrate that training with these explanations improves factual precision and provides a more effective supervision signal for downstream gene expression prediction. These results underscore the importance of reliable mechanistic reasoning for virtual cells, achieved through the synergy of multi-agent and rigorous verification.
title Towards Autonomous Mechanistic Reasoning in Virtual Cells
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.11661