{
  "abstract": "Single-cell foundation models (scFMs) are transforming computational biology by enabling generalizable, task-agnostic representations for versatile single-cell analysis. Despite their progress in facilitating rapid deployment for downstream tasks, off-the-shelf scFMs still have some overlooked concerns: (I) (Pretraining Cost.) Pretrain-based scFMs necessitate pretraining on a vast volume of cells, rendering it draining resources in applications. (II) (Heterogeneous Gap.) Large Language Models (LLM)-based scFMs ignore the tremendous heterogeneous gap between LLM textual and raw cellular spaces, leading to insufficient capability when facing downstream tasks. To this end, we introduce RAGCell, a versatile single-cell analysis framework that achieves a double-win in both cost-effectiveness and high performance. The success of RAGCell lies in two key aspects: Leveraging LLMs to construct cell-level and feature-level knowledge databases, which serve as supervision signals for training the cell model and significantly reduce the training cost ($>$pretrain-based scFMs). Aligning cell representations with text embeddings from the bi-level knowledge databases, enabling knowledge transfer from textual spaces to cellular spaces and effectively mitigating the heterogeneous gap ($>$LLM-based scFMs). Through extensive experiments on six downstream single-cell analysis tasks, we demonstrate that RAGCell achieves outstanding performance compared to state-of-the-art scFMs while operating at less than $\\sim$1/10 the cost of pretrain-based scFMs.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.14147",
  "author_total": 13,
  "authors": [
    {
      "name": "Tianyu Liu"
    },
    {
      "name": "Fan Zhang"
    },
    {
      "name": "Jiayuan Chen"
    },
    {
      "name": "Kun Wang"
    },
    {
      "name": "Haoxuan Li"
    },
    {
      "name": "Shengju Qian"
    },
    {
      "name": "Zhihong Zhu"
    },
    {
      "name": "Donghao Zhou"
    },
    {
      "name": "Hao Wu"
    },
    {
      "name": "Ziheng Zhang"
    },
    {
      "name": "Zhenxi Lin"
    },
    {
      "name": "Xian Wu"
    },
    {
      "name": "Yefeng Zheng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e226rqbch8hn3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.14147",
  "fulltext_url": null,
  "id": "e226rqbch8hn3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.14147",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.GN"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.14147",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e226rqbch8hn3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:30Z",
      "native_id": "2609.14147",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.14147"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis",
  "title_text": "RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:30Z",
  "url": "https://research.draconitic.com/paper/e226rqbch8hn3",
  "venue": "arXiv",
  "versions": []
}