Journal article · 2026 · Open access
Generalizability of Large Language Model-Based Agents: A Comprehensive Survey
ACM Computing Surveys, 58(10), 1–44 · Published 7 February 2026 · DOI 10.1145/3794858
In brief
“Generalizability of Large Language Model-Based Agents: A Comprehensive Survey” is a 2026 journal article by Minxing Zhang and 5 co-authors, published in ACM Computing Surveys. OpenAlex counts 15 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 15
- Most cited in
- 2026 (14)
- Field-weighted impact
- 19.53
- References
- 119
- Authors
- 6
Abstract
Large Language Model (LLM)-based agents have recently emerged as a new paradigm that extends the capabilities of LLMs beyond text generation to dynamic interaction with external environments. A critical challenge lies in ensuring their g eneralizability – the ability to maintain consistently high performance across varied instructions, tasks, environments, and domains, especially those different from the agent’s fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. We provide the first comprehensive review of generalizability in LLM-based agents. We begin by clarifying the definition and boundaries of agent generalizability. We then review existing benchmarks. Next, we categorize strategies for improving generalizability into three groups: methods targeting the backbone LLM, targeting agent components, and targeting their interactions. Furthermore, we introduce the distinction between g eneralizable frameworks and g eneralizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify future directions, including the development of standardized evaluation frameworks, variance- and cost-based metrics, and hybrid approaches that integrate methodological innovations with agent architecture-level designs. We aim to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse real-world applications.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, M., Yang, Y., Xie, R., Dhingra, B., ZHOU, S., & Pei, J. (2026). Generalizability of Large Language Model-Based Agents: A Comprehensive Survey. ACM Computing Surveys, 58(10), 1–44. https://doi.org/10.1145/3794858
MLA 9
Zhang, Minxing, et al. “Generalizability of Large Language Model-Based Agents: A Comprehensive Survey.” ACM Computing Surveys, vol. 58, no. 10, 2026, pp. 1–44. https://doi.org/10.1145/3794858.
Chicago
Zhang, Minxing, Yi Yang, Roy Xie, Bhuwan Dhingra, S ZHOU, and Jian Pei. 2026. “Generalizability of Large Language Model-Based Agents: A Comprehensive Survey.” ACM Computing Surveys 58 (10): 1–44. https://doi.org/10.1145/3794858.
Harvard
Zhang, M. et al. (2026) ‘Generalizability of Large Language Model-Based Agents: A Comprehensive Survey’, ACM Computing Surveys, 58(10), pp. 1–44. doi:10.1145/3794858.
IEEE
M. Zhang, Y. Yang, R. Xie, B. Dhingra, S. ZHOU, and J. Pei, “Generalizability of Large Language Model-Based Agents: A Comprehensive Survey,” ACM Computing Surveys, vol. 58, no. 10, pp. 1–44, 2026, doi: 10.1145/3794858.
BibTeX
@article{zhang2026generalizability,
title = {{Generalizability of Large Language Model-Based Agents: A Comprehensive Survey}},
author = {Zhang, Minxing and Yang, Yi and Xie, Roy and Dhingra, Bhuwan and ZHOU, S and Pei, Jian},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {10},
pages = {1--44},
doi = {10.1145/3794858},
url = {https://doi.org/10.1145/3794858}
}
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
- LLM agents
- generalizability
- large language models
- benchmarking
- evaluation metrics
- agent architecture
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?
Zhang, M., Yang, Y., Xie, R., Dhingra, B., ZHOU, S., & Pei, J. (2026). Generalizability of Large Language Model-Based Agents: A Comprehensive Survey. ACM Computing Surveys, 58(10), 1–44. https://doi.org/10.1145/3794858
How many times has this paper been cited?
15 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 arXiv (Cornell University).
Who wrote this paper?
Minxing Zhang, Yi Yang, Roy Xie, Bhuwan Dhingra, S ZHOU, Jian Pei.
What is the DOI of this paper?
10.1145/3794858. The permanent link is https://doi.org/10.1145/3794858.
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.