scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
Abstract
We present scPilot, the first systematic framework to practice omics-native reasoning: a large language model (LLM) converses in natural language while directly inspecting single-cell RNA-seq data and on-demand bioinformatics tools. scPilot converts core single-cell analyses, i.e., cell-type annotation, developmental-trajectory reconstruction, and transcription-factor targeting, into step-by-step reasoning problems that the model must solve, justify, and, when needed, revise with new evidence. To measure progress, we release scBench, a suite of 9 expertly curated datasets and graders that faithfully evaluate the omics-native reasoning capability of scPilot w.r.t various LLMs. Experiments with o1 show that iterative omics-native reasoning lifts average accuracy by 11% for cell-type annotation and Gemini-2.5-Pro cuts trajectory graph-edit distance by 30% versus one-shot prompting, while generating transparent reasoning traces explain marker gene ambiguity and regulatory logic. By grounding LLMs in raw omics data, scPilot enables auditable, interpretable, and diagnostically informative single-cell analyses. Code, data, and package are available at https://github.com/maitrix-org/scPilot
Cite
@article{arxiv.2602.11609,
title = {scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery},
author = {Yiming Gao and Zhen Wang and Jefferson Chen and Mark Antkowiak and Mengzhou Hu and JungHo Kong and Dexter Pratt and Jieyuan Liu and Enze Ma and Zhiting Hu and Eric P. Xing},
journal= {arXiv preprint arXiv:2602.11609},
year = {2026}
}
Comments
Accepted at NeurIPS 2025 Main Conference