Xu, W.; Poussi, E.; Zhong, Q.; Zeng, Z.; Zou, C.; Wang, X.; Lu, Y.; Cui, M.; Okamura, D.; Huang, C.; Ding, J.; Zhao, Z.; Yang, Y.; Pan, X.; Vijay, V.; Konno, N.; Liu, N.; Li, L.; Ma, X. R.; Conley, S. D.; Kern, C.; Goodyer, W. R.; Bintu, B.; Zhu, Q.; Chi, N. C.; He, J.; Rognoni, L.; Zhang, X.; Wu, J.; Ellison, D.; Rabinovitch, M.; Engreitz, J. M.; Qiu, X.

The convergence of large language model-powered autonomous agent systems and single-cell biology promises a paradigm shift in biomedical discovery. However, existing biological agent systems, building upon single-agent architectures, are narrowly specialized or overly general, limiting applications to routine analyses. We introduce PantheonOS (PantheonOS.stanford.edu), an evolvable, privacy-preserving multi-agent framework designed to reconcile generality with domain specificity. Critically, PantheonOS enables agentic code evolution, allowing evolving state-of-the-art batch correction and our reinforcement-learning augmented gene panel selection algorithms to achieve super-human performance. PantheonOS drives biological discoveries across systems: uncovering asymmetric paracrine Cer1-Nodal inhibition in proximal-distal axis formation of novel early mouse embryo 3D data; integrating human fetal heart multi-omics with whole-heart data to reveal molecular programs underpin heart diseases; and adaptively selecting virtual cell models to predict cardiac regulatory and perturbation effects. Together, PantheonOS points towards a future where scientific discoveries are increasingly driven by self-evolving AI systems across biology and beyond.