Journal article · 2026 · Open access
Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems
Journal of Artificial Intelligence for Automation, 1(2) · Published 17 July 2026 · DOI 10.53941/jaia.2026.100012
In brief
“Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems” is a 2026 journal article by Jing Bi and 6 co-authors, published in Journal of Artificial Intelligence for Automation. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of Artificial Intelligence for Automation.
- Citations
- 0
- References
- 102
- Authors
- 7
Abstract
Foundation models have improved the reasoning and generation ability of artificial intelligence systems. However, they are difficult to deploy in edge environments with limited computation, memory, and data access. Small models are easier to run on edge devices. They support fast and low-latency inference, but they often lack global semantic reasoning and cross-domain generalization. This gap between model ability and deployment cost motivates large–small model collaboration in cloud–edge systems. This survey provides a systematic review and a knowledge-floworiented taxonomy of such collaboration. It focuses on how cloud-side large models and edge-side small models share, update, and coordinate knowledge. We review knowledge distillation, split inference, federated and continual adaptation, and elastic offloading. We also cover lightweight deployment, modular expert design, privacyaware coordination, and agent-driven orchestration. Unlike surveys on edge intelligence, federated learning, model compression, TinyML, or cloud–edge resource scheduling, this survey centers on model collaboration. We treat large–small collaboration as a knowledge-centered problem linked to real deployment constraints. We further discuss trade-offs in accuracy, latency, bandwidth, privacy, energy efficiency, adaptability, and lifecycle management. Finally, we identify open challenges for trustworthy, sustainable, and self-evolving cloud–edge collaborative intelligence.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Bi, J., Yang, Y., Yuan, H., Wang, Z., Li, J., Zhai, J., & Zhang, J. (2026). Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems. Journal of Artificial Intelligence for Automation, 1(2). https://doi.org/10.53941/jaia.2026.100012
MLA 9
Bi, Jing, et al. “Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems.” Journal of Artificial Intelligence for Automation, vol. 1, no. 2, 2026. https://doi.org/10.53941/jaia.2026.100012.
Chicago
Bi, Jing, Yaxi Yang, Haitao Yuan, Ziqi Wang, Jiayi Li, Jiahui Zhai, and Jia Zhang. 2026. “Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems.” Journal of Artificial Intelligence for Automation 1 (2). https://doi.org/10.53941/jaia.2026.100012.
Harvard
Bi, J. et al. (2026) ‘Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems’, Journal of Artificial Intelligence for Automation, 1(2). doi:10.53941/jaia.2026.100012.
IEEE
J. Bi et al., “Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems,” Journal of Artificial Intelligence for Automation, vol. 1, no. 2, 2026, doi: 10.53941/jaia.2026.100012.
BibTeX
@article{bi2026towards,
title = {{Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems}},
author = {Bi, Jing and Yang, Yaxi and Yuan, Haitao and Wang, Ziqi and Li, Jiayi and Zhai, Jiahui and Zhang, Jia},
journal = {Journal of Artificial Intelligence for Automation},
year = {2026},
volume = {1},
number = {2},
doi = {10.53941/jaia.2026.100012},
url = {https://doi.org/10.53941/jaia.2026.100012}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- edge computing
- knowledge distillation
- split inference
- federated learning
- continual learning
- model offloading
- lightweight model deployment
- agent 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?
Bi, J., Yang, Y., Yuan, H., Wang, Z., Li, J., Zhai, J., & Zhang, J. (2026). Towards a Unified Framework for Large–Small Model Collaboration in Cloud–Edge Systems. Journal of Artificial Intelligence for Automation, 1(2). https://doi.org/10.53941/jaia.2026.100012
How many times has this paper been cited?
0 times, according to OpenAlex on 19 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 Journal of Artificial Intelligence for Automation: sign in and open the PDF from this page.
Who wrote this paper?
Jing Bi, Yaxi Yang, Haitao Yuan, Ziqi Wang, Jiayi Li, Jiahui Zhai, Jia Zhang.
What is the DOI of this paper?
10.53941/jaia.2026.100012, permanently at https://doi.org/10.53941/jaia.2026.100012. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 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.