Journal article · 2026 · Open access

Benchmarking LLM-based agents for single-cell omics analysis

Yang Liu, Lu Zhou, Xiawei Du, Ruikun He, Xuguang Zhang, Rongbo Shen, Yixue Li

Genome biology, 27(1) · Published 25 February 2026 · DOI 10.1186/s13059-026-03998-z

Open full textCite this paper

In brief

“Benchmarking LLM-based agents for single-cell omics analysis” is a 2026 journal article by Yang Liu and 6 co-authors, published in Genome biology. OpenAlex counts 14 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Genome biology.

Citations
14
Most cited in
2026 (14)
Field-weighted impact
31.48
References
84
Authors
7

Abstract

BACKGROUND: The surge in single-cell omics data exposes limitations in traditional, manually defined analysis workflows. AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable decisions, and real-time knowledge fusion. However, the lack of a comprehensive benchmark critically hinders progress. RESULTS: We introduce a novel benchmarking evaluation system to rigorously assess agent capabilities in single-cell omics analysis. This system comprises: a unified platform compatible with diverse agent frameworks and LLMs; multidimensional metrics assessing cognitive program synthesis, collaboration, execution efficiency, bioinformatics knowledge integration, and task completion quality; and 50 diverse real-world single-cell omics analysis tasks spanning multi-omics, species, and sequencing technologies. Our evaluation reveals that Grok3-beta achieves state-of-the-art performance among tested agent frameworks. Multi-agent frameworks significantly enhance collaboration and execution efficiency over single-agent approaches through specialized role division. Attribution analyses of agent capabilities identify that high-quality code generation is crucial for task success, and self-reflection has the most significant overall impact, followed by retrieval-augmented generation (RAG) and planning. CONCLUSIONS: This work highlights persistent challenges in code generation, long-context handling, and context-aware knowledge retrieval, providing a critical empirical foundation and best practices for developing robust AI agents in computational biology.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Liu, Y., Zhou, L., Du, X., He, R., Zhang, X., Shen, R., & Li, Y. (2026). Benchmarking LLM-based agents for single-cell omics analysis. Genome biology, 27(1). https://doi.org/10.1186/s13059-026-03998-z

MLA 9

Liu, Yang, et al. “Benchmarking LLM-based agents for single-cell omics analysis.” Genome biology, vol. 27, no. 1, 2026. https://doi.org/10.1186/s13059-026-03998-z.

Chicago

Liu, Yang, Lu Zhou, Xiawei Du, Ruikun He, Xuguang Zhang, Rongbo Shen, and Yixue Li. 2026. “Benchmarking LLM-based agents for single-cell omics analysis.” Genome biology 27 (1). https://doi.org/10.1186/s13059-026-03998-z.

Harvard

Liu, Y. et al. (2026) ‘Benchmarking LLM-based agents for single-cell omics analysis’, Genome biology, 27(1). doi:10.1186/s13059-026-03998-z.

IEEE

Y. Liu et al., “Benchmarking LLM-based agents for single-cell omics analysis,” Genome biology, vol. 27, no. 1, 2026, doi: 10.1186/s13059-026-03998-z.

BibTeX

@article{liu2026benchmarking,
  title     = {{Benchmarking LLM-based agents for single-cell omics analysis}},
  author    = {Liu, Yang and Zhou, Lu and Du, Xiawei and He, Ruikun and Zhang, Xuguang and Shen, Rongbo and Li, Yixue},
  journal   = {Genome biology},
  year      = {2026},
  volume    = {27},
  number    = {1},
  doi       = {10.1186/s13059-026-03998-z},
  url       = {https://doi.org/10.1186/s13059-026-03998-z}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management

  • LLM agents
  • benchmarking
  • multi-agent systems
  • code generation
  • retrieval-augmented generation
  • multi-omics integration
  • agent cooperation
  • computational biology

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Liu, Y., Zhou, L., Du, X., He, R., Zhang, X., Shen, R., & Li, Y. (2026). Benchmarking LLM-based agents for single-cell omics analysis. Genome biology, 27(1). https://doi.org/10.1186/s13059-026-03998-z

How many times has this paper been cited?

14 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Genome biology: sign in and open the full text from this page.

Who wrote this paper?

Yang Liu, Lu Zhou, Xiawei Du, Ruikun He, Xuguang Zhang, Rongbo Shen, Yixue Li.

What is the DOI of this paper?

10.1186/s13059-026-03998-z, permanently at https://doi.org/10.1186/s13059-026-03998-z. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.