Single-cell RNA-seq (scRNA-seq) enables atlas-scale profiling of complex tissues, revealing rare lineages and transient states. Yet, assigning biologically valid cell identities remains a bottleneck because markers are tissue- and state-dependent, and novel states lack references. We present CellMaster, an AI agent that mimics expert practice for zero-shot cell-type annotation. Unlike existing automated tools, CellMaster leverages LLM-encoded knowledge (e.g., GPT-4o) to perform on-the-fly annotation with interpretable rationales, without pre-training or fixed marker databases. Across 9 datasets spanning 8 tissues, CellMaster improved accuracy by 7.1% over best-performing baselines (including CellTypist and scTab) in automatic mode. With human-in-the-loop refinement, this advantage increased to 18.6%, with a 22.1% gain on subtype populations. The system demonstrates particular strength in rare and novel cell states where baselines often fail. Source code and the web application are available at \href{https://github.com/AnonymousGym/CellMaster}{https://github.com/AnonymousGym/CellMaster}.
@article{arxiv.2602.13346,
title = {CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis},
author = {Zhen Wang and Yiming Gao and Jieyuan Liu and Enze Ma and Jefferson Chen and Mark Antkowiak and Mengzhou Hu and JungHo Kong and Dexter Pratt and Zhiting Hu and Wei Wang and Trey Ideker and Eric P. Xing},
journal= {arXiv preprint arXiv:2602.13346},
year = {2026}
}