{"ID":2886848,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02276","arxiv_id":"2508.02276","title":"CellForge: Agentic Design of Virtual Cell Models","abstract":"Virtual cell modeling aims to predict cellular responses to diverse perturbations but faces challenges from biological complexity, multimodal data heterogeneity, and the need for interdisciplinary expertise. We introduce CellForge, a multi-agent framework that autonomously designs and synthesizes neural network architectures tailored to specific single-cell datasets and perturbation tasks. Given raw multi-omics data and task descriptions, CellForge discovers candidate architectures through collaborative reasoning among specialized agents, then generates executable implementations. Our core contribution is the framework itself: showing that multi-agent collaboration mechanisms - rather than manual human design or single-LLM prompting - can autonomously produce executable, high-quality computational methods. This approach goes beyond conventional hyperparameter tuning by enabling entirely new architectural components such as trajectory-aware encoders and perturbation diffusion modules to emerge from agentic deliberation. We evaluate CellForge on six datasets spanning gene knockouts, drug treatments, and cytokine stimulations across multiple modalities (scRNA-seq, scATAC-seq, CITE-seq). The results demonstrate that the models generated by CellForge are highly competitive with established baselines, while revealing systematic patterns of architectural innovation. CellForge highlights the scientific value of multi-agent frameworks: collaboration among specialized agents enables genuine methodological innovation and executable solutions that single agents or human experts cannot achieve. This represents a paradigm shift toward autonomous scientific method development in computational biology. Code is available at https://github.com/gersteinlab/CellForge.","short_abstract":"Virtual cell modeling aims to predict cellular responses to diverse perturbations but faces challenges from biological complexity, multimodal data heterogeneity, and the need for interdisciplinary expertise. We introduce CellForge, a multi-agent framework that autonomously designs and synthesizes neural network archite...","url_abs":"https://arxiv.org/abs/2508.02276","url_pdf":"https://arxiv.org/pdf/2508.02276v2","authors":"[\"Xiangru Tang\",\"Zhuoyun Yu\",\"Jiapeng Chen\",\"Yan Cui\",\"Daniel Shao\",\"Weixu Wang\",\"Fang Wu\",\"Yuchen Zhuang\",\"Wenqi Shi\",\"Zhi Huang\",\"Arman Cohan\",\"Xihong Lin\",\"Fabian Theis\",\"Smita Krishnaswamy\",\"Mark Gerstein\"]","published":"2025-08-04T10:43:31Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CL\",\"q-bio.QM\"]","methods":"[\"Diffusion Model\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":611370,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2886848,"paper_url":"https://arxiv.org/abs/2508.02276","paper_title":"CellForge: Agentic Design of Virtual Cell Models","repo_url":"https://github.com/gersteinlab/CellForge","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}