Journal article · 2026 · Open access
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
IEEE Access, 14, 84237–84285 · Published 1 January 2026 · DOI 10.1109/access.2026.3698694
In brief
“From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review” is a 2026 journal article by Mohamed Amine Ferrag and 2 co-authors, published in IEEE Access. OpenAlex counts 344 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Access.
- Citations
- 344
- Most cited in
- 2026 (257)
- Field-weighted impact
- 248.74
- References
- 234
- Authors
- 3
Abstract
Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the growing need for standardized evaluation and integration, we systematically consolidate these fragmented efforts into a unified framework. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments. Furthermore, we review AI-agent frameworks introduced between 2023 and 2025 that integrate large language models with modular toolkits to enable autonomous decision-making and multi-step reasoning. Moreover, we present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, chemical reasoning, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance. We then survey key agent-to-agent collaboration protocols, namely the Agent Communication Protocol (ACP), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A). Finally, we discuss recommendations for future research, focusing on advanced reasoning strategies, failure modes in multi-agent LLM systems, automated scientific discovery, dynamic tool integration via reinforcement learning, integrated search capabilities, and security vulnerabilities in agent protocols.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ferrag, M. A., Tihanyi, N., & Debbah, M. A. (2026). From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review. IEEE Access, 14, 84237–84285. https://doi.org/10.1109/access.2026.3698694
MLA 9
Ferrag, Mohamed Amine, et al. “From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review.” IEEE Access, vol. 14, 2026, pp. 84237–84285. https://doi.org/10.1109/access.2026.3698694.
Chicago
Ferrag, Mohamed Amine, Norbert Tihanyi, and Merouane Abdelkader Debbah. 2026. “From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review.” IEEE Access 14: 84237–84285. https://doi.org/10.1109/access.2026.3698694.
Harvard
Ferrag, M. A., Tihanyi, N. and Debbah, M. A. (2026) ‘From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review’, IEEE Access, 14, pp. 84237–84285. doi:10.1109/access.2026.3698694.
IEEE
M. A. Ferrag, N. Tihanyi, and M. A. Debbah, “From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review,” IEEE Access, vol. 14, pp. 84237–84285, 2026, doi: 10.1109/access.2026.3698694.
BibTeX
@article{ferrag2026from,
title = {{From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review}},
author = {Ferrag, Mohamed Amine and Tihanyi, Norbert and Debbah, Merouane Abdelkader},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {84237--84285},
doi = {10.1109/access.2026.3698694},
url = {https://doi.org/10.1109/access.2026.3698694}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 86 | |
| 2026 | 257 |
Its field-weighted citation impact is 248.74: it has been cited 248.74 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- large language models
- autonomous AI agents
- AI agent evaluation
- agent frameworks
- agent communication protocols
- mathematical problem solving
- code generation
- task orchestration
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ferrag, M. A., Tihanyi, N., & Debbah, M. A. (2026). From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review. IEEE Access, 14, 84237–84285. https://doi.org/10.1109/access.2026.3698694
How many times has this paper been cited?
344 times, according to OpenAlex on 21 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 IEEE Access: sign in and open the full text from this page.
Who wrote this paper?
Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Abdelkader Debbah.
What is the DOI of this paper?
10.1109/access.2026.3698694, permanently at https://doi.org/10.1109/access.2026.3698694. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 21 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.