Journal article · 2026 · Open access

A Survey of Large-Model-Based AI Agents

Chuan Qin, Long Jin

Tsinghua Science & Technology · Published 30 June 2026 · DOI 10.26599/tst.2026.9010072

Free PDFView at the publisherCite this paper

In brief

“A Survey of Large-Model-Based AI Agents” is a 2026 journal article by Chuan Qin and Long Jin, published in Tsinghua Science & Technology. OpenAlex counts 1 citations as of 15 November 2026, which puts it in the top 9% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Tsinghua Science & Technology.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.40
References
173
Authors
2

Abstract

Advances in large models (LMs) have catalyzed a paradigm shift in artificial intelligence (AI), enabling the development of autonomous agents capable of complex reasoning, planning, and interaction with both digital and physical environments. As this field has expanded at an unprecedented rate, a comprehensive and structured overview is essential to consolidate current knowledge and guide future innovations. To address this need, this survey provides a holistic review of LM-based AI agents. First, we deconstruct the core architecture of modern LM-based agents and examine the interplay among key modules, including reasoning, perception, memory, planning, action, and learning. Subsequently, we systematically analyze the evaluation landscape, summarizing current benchmarks, metrics, and module-specific performance trade-offs. Furthermore, we survey the transformative impact of these agents across a broad spectrum of applications, ranging from digital domains to embodied systems. This study concludes by identifying critical challenges and future directions, thus offering a roadmap for the next generation of LM-based AI agents.

Cite this paper

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

APA 7

Qin, C., & Jin, L. (2026). A Survey of Large-Model-Based AI Agents. Tsinghua Science & Technology. https://doi.org/10.26599/tst.2026.9010072

MLA 9

Qin, Chuan, and Long Jin. “A Survey of Large-Model-Based AI Agents.” Tsinghua Science & Technology, 2026. https://doi.org/10.26599/tst.2026.9010072.

Chicago

Qin, Chuan and Long Jin. 2026. “A Survey of Large-Model-Based AI Agents.” Tsinghua Science & Technology. https://doi.org/10.26599/tst.2026.9010072.

Harvard

Qin, C. and Jin, L. (2026) ‘A Survey of Large-Model-Based AI Agents’, Tsinghua Science & Technology. doi:10.26599/tst.2026.9010072.

IEEE

C. Qin and L. Jin, “A Survey of Large-Model-Based AI Agents,” Tsinghua Science & Technology, 2026, doi: 10.26599/tst.2026.9010072.

BibTeX

@article{qin2026survey,
  title     = {{A Survey of Large-Model-Based AI Agents}},
  author    = {Qin, Chuan and Jin, Long},
  journal   = {Tsinghua Science \& Technology},
  year      = {2026},
  doi       = {10.26599/tst.2026.9010072},
  url       = {https://doi.org/10.26599/tst.2026.9010072}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning

  • large language models
  • AI agents
  • autonomous agents
  • agent architecture
  • reasoning
  • perception
  • memory
  • planning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Qin, C., & Jin, L. (2026). A Survey of Large-Model-Based AI Agents. Tsinghua Science & Technology. https://doi.org/10.26599/tst.2026.9010072

How many times has this paper been cited?

1 times, according to OpenAlex on 15 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: read the free full text at Tsinghua Science & Technology.

Who wrote this paper?

Chuan Qin, Long Jin.

What is the DOI of this paper?

10.26599/tst.2026.9010072. The permanent link is https://doi.org/10.26599/tst.2026.9010072.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.