Conference paper · 2026 · Open access
A Capacity-Aware Task Allocation Scheme in Internet of Agents
International Conference on Communications, 1–6 · Published 24 May 2026 · DOI 10.1109/icc59461.2026.11588028
In brief
“A Capacity-Aware Task Allocation Scheme in Internet of Agents” is a 2026 conference paper by Jintao Wei and 5 co-authors, published in International Conference on Communications. 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 International Conference on Communications.
- Citations
- 0
- References
- 15
- Authors
- 6
Abstract
As large language model (LLM)–driven agents proliferate, the Internet of Agents (IoA) is emerging as a decentralized ecosystem of heterogeneous, autonomous agents. Achieving large-scale cooperation in such systems requires reliable agent capability modeling and adaptive task allocation. However, existing approaches often rely on self-reported capabilities and overlook the workflow-dependent nature of coalition capability. This paper presents a capacity-aware task allocation framework for IoA that addresses these gaps through three components: i) a dynamic capability verification model that transforms self-declared skills into empirical quality and throughput metrics; ii) a topology-aware coalition capability aggregation method that models intra-coalition workflows as directed acyclic graphs (DAGs) and computes coalition capabilities via both serial (multiplicative) and parallel (additive) reductions; and iii) a many-to-one stable matching formulation with a low-cost two-sided iterative algorithm to obtain optimal and stable task assignments under coalition capacity constraints. Extensive simulations demonstrate the proposed framework’s effectiveness and scalability compared with baseline methods.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wei, J., Wang, Y., Guo, S., Su, Z., Luan, T. H., & Peng, H. (2026). A Capacity-Aware Task Allocation Scheme in Internet of Agents. International Conference on Communications, 1–6. https://doi.org/10.1109/icc59461.2026.11588028
MLA 9
Wei, Jintao, et al. “A Capacity-Aware Task Allocation Scheme in Internet of Agents.” International Conference on Communications, 2026, pp. 1–6. https://doi.org/10.1109/icc59461.2026.11588028.
Chicago
Wei, Jintao, Yuntao Wang, Shaolong Guo, Zhou Su, Tom H. Luan, and Haixia Peng. 2026. “A Capacity-Aware Task Allocation Scheme in Internet of Agents.” International Conference on Communications: 1–6. https://doi.org/10.1109/icc59461.2026.11588028.
Harvard
Wei, J. et al. (2026) ‘A Capacity-Aware Task Allocation Scheme in Internet of Agents’, International Conference on Communications, pp. 1–6. doi:10.1109/icc59461.2026.11588028.
IEEE
J. Wei, Y. Wang, S. Guo, Z. Su, T. H. Luan, and H. Peng, “A Capacity-Aware Task Allocation Scheme in Internet of Agents,” International Conference on Communications, pp. 1–6, 2026, doi: 10.1109/icc59461.2026.11588028.
BibTeX
@inproceedings{wei2026capacity,
title = {{A Capacity-Aware Task Allocation Scheme in Internet of Agents}},
author = {Wei, Jintao and Wang, Yuntao and Guo, Shaolong and Su, Zhou and Luan, Tom H. and Peng, Haixia},
booktitle = {International Conference on Communications},
year = {2026},
pages = {1--6},
doi = {10.1109/icc59461.2026.11588028},
url = {https://doi.org/10.1109/icc59461.2026.11588028}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Internet of Agents
- task allocation
- LLM agents
- directed acyclic graphs
- stable matching
- many-to-one matching
- agent cooperation
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?
Wei, J., Wang, Y., Guo, S., Su, Z., Luan, T. H., & Peng, H. (2026). A Capacity-Aware Task Allocation Scheme in Internet of Agents. International Conference on Communications, 1–6. https://doi.org/10.1109/icc59461.2026.11588028
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 International Conference on Communications: sign in and open the full text from this page.
Who wrote this paper?
Jintao Wei, Yuntao Wang, Shaolong Guo, Zhou Su, Tom H. Luan, Haixia Peng.
What is the DOI of this paper?
10.1109/icc59461.2026.11588028, permanently at https://doi.org/10.1109/icc59461.2026.11588028. 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.