Journal article · 2026 · Open access

From language to action: a review of large language models as autonomous agents and tool users

Sadia Sultana Chowa, Riasad Alvi, S M Asif Ur Rahman, Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Md Rafiqul Islam, Mukhtar Hussain, Sami Azam

Artificial Intelligence Review, 59(2) · Published 6 January 2026 · DOI 10.1007/s10462-025-11471-9

Read the free full textCite this paper

In brief

“From language to action: a review of large language models as autonomous agents and tool users” is a 2026 journal article by Sadia Sultana Chowa and 7 co-authors, published in Artificial Intelligence Review. OpenAlex counts 99 citations as of 15 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Artificial Intelligence Review.

Citations
99
Most cited in
2026 (91)
Field-weighted impact
127.83
References
132
Authors
8

Abstract

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A-ranked and Q1 journals. A structured analysis of the LLM agents’ architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLMs, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we have evaluated current benchmarks and assessment protocols and provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.

Cite this paper

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

APA 7

Chowa, S. S., Alvi, R., Rahman, S. M. A. U., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026). From language to action: a review of large language models as autonomous agents and tool users. Artificial Intelligence Review, 59(2). https://doi.org/10.1007/s10462-025-11471-9

MLA 9

Chowa, Sadia Sultana, et al. “From language to action: a review of large language models as autonomous agents and tool users.” Artificial Intelligence Review, vol. 59, no. 2, 2026. https://doi.org/10.1007/s10462-025-11471-9.

Chicago

Chowa, Sadia Sultana, Riasad Alvi, S M Asif Ur Rahman, Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Md Rafiqul Islam, Mukhtar Hussain, and Sami Azam. 2026. “From language to action: a review of large language models as autonomous agents and tool users.” Artificial Intelligence Review 59 (2). https://doi.org/10.1007/s10462-025-11471-9.

Harvard

Chowa, S. S. et al. (2026) ‘From language to action: a review of large language models as autonomous agents and tool users’, Artificial Intelligence Review, 59(2). doi:10.1007/s10462-025-11471-9.

IEEE

S. S. Chowa et al., “From language to action: a review of large language models as autonomous agents and tool users,” Artificial Intelligence Review, vol. 59, no. 2, 2026, doi: 10.1007/s10462-025-11471-9.

BibTeX

@article{chowa2026from,
  title     = {{From language to action: a review of large language models as autonomous agents and tool users}},
  author    = {Chowa, Sadia Sultana and Alvi, Riasad and Rahman, S M Asif Ur and Rahman, Md. Abdur and Raiaan, Mohaimenul Azam Khan and Islam, Md Rafiqul and Hussain, Mukhtar and Azam, Sami},
  journal   = {Artificial Intelligence Review},
  year      = {2026},
  volume    = {59},
  number    = {2},
  doi       = {10.1007/s10462-025-11471-9},
  url       = {https://doi.org/10.1007/s10462-025-11471-9}
}

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
  • autonomous agents
  • tool use
  • multi-agent systems
  • LLM agents
  • LLM reasoning
  • LLM memory
  • prompting

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?

Chowa, S. S., Alvi, R., Rahman, S. M. A. U., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026). From language to action: a review of large language models as autonomous agents and tool users. Artificial Intelligence Review, 59(2). https://doi.org/10.1007/s10462-025-11471-9

How many times has this paper been cited?

99 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 Artificial Intelligence Review.

Who wrote this paper?

Sadia Sultana Chowa, Riasad Alvi, S M Asif Ur Rahman, Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Md Rafiqul Islam, Mukhtar Hussain, Sami Azam.

What is the DOI of this paper?

10.1007/s10462-025-11471-9. The permanent link is https://doi.org/10.1007/s10462-025-11471-9.

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.