Conference paper · 2026 · Open access

SWARM-LLM: Collaborative Inference for Edge-based Small Language Models

Mostafa H. Dahshan, Quazi Mamun, Tanmoy Debnath

IEEE Vehicular Technology Conference, 1–8 · Published 1 June 2026 · DOI 10.1109/vtc2026-spring68026.2026.11757728

Open full textCite this paper

In brief

“SWARM-LLM: Collaborative Inference for Edge-based Small Language Models” is a 2026 conference paper by Mostafa H. Dahshan and 2 co-authors, published in IEEE Vehicular Technology Conference. 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 IEEE Vehicular Technology Conference.

Citations
0
References
10
Authors
3

Abstract

Large language models (LLMs) provide strong performance across a wide range of tasks but are typically hosted on centralised cloud infrastructure, incurring significant bandwidth, latency, and privacy costs. In contrast, small language models (SLMs) can run on edge devices but have limited capability and robustness. This paper introduces SWARM-LLM, a routing and collaboration layer that coordinates a small swarm of edge-hosted SLMs with an optional cloud foundation model (FM). SWARM-LLM decides, for each query, whether to answer locally, collaborate with peer SLMs, or "summon" a cloud FM, using lightweight uncertainty estimates and safety signals. We implement a working prototype on commodity hardware with three heterogeneous SLMs and a 70B-parameter cloud FM accessed via API, and evaluate it on a controlled study workload of easy, hard, and safety-oriented queries. Our results show that SWARM-LLM substantially improves performance on hard questions compared to an edge-only deployment, while limiting cloud usage to roughly one quarter of queries, illustrating a practical trade-off between accuracy, latency, and cost for privacy-conscious edge deployments. The implementation code is available at the GitHub repository https://github.com/mdahshan/swarm_llm.

Cite this paper

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

APA 7

Dahshan, M. H., Mamun, Q., & Debnath, T. (2026). SWARM-LLM: Collaborative Inference for Edge-based Small Language Models. IEEE Vehicular Technology Conference, 1–8. https://doi.org/10.1109/vtc2026-spring68026.2026.11757728

MLA 9

Dahshan, Mostafa H., et al. “SWARM-LLM: Collaborative Inference for Edge-based Small Language Models.” IEEE Vehicular Technology Conference, 2026, pp. 1–8. https://doi.org/10.1109/vtc2026-spring68026.2026.11757728.

Chicago

Dahshan, Mostafa H., Quazi Mamun, and Tanmoy Debnath. 2026. “SWARM-LLM: Collaborative Inference for Edge-based Small Language Models.” IEEE Vehicular Technology Conference: 1–8. https://doi.org/10.1109/vtc2026-spring68026.2026.11757728.

Harvard

Dahshan, M. H., Mamun, Q. and Debnath, T. (2026) ‘SWARM-LLM: Collaborative Inference for Edge-based Small Language Models’, IEEE Vehicular Technology Conference, pp. 1–8. doi:10.1109/vtc2026-spring68026.2026.11757728.

IEEE

M. H. Dahshan, Q. Mamun, and T. Debnath, “SWARM-LLM: Collaborative Inference for Edge-based Small Language Models,” IEEE Vehicular Technology Conference, pp. 1–8, 2026, doi: 10.1109/vtc2026-spring68026.2026.11757728.

BibTeX

@inproceedings{dahshan2026swarm,
  title     = {{SWARM-LLM: Collaborative Inference for Edge-based Small Language Models}},
  author    = {Dahshan, Mostafa H. and Mamun, Quazi and Debnath, Tanmoy},
  booktitle = {IEEE Vehicular Technology Conference},
  year      = {2026},
  pages     = {1--8},
  doi       = {10.1109/vtc2026-spring68026.2026.11757728},
  url       = {https://doi.org/10.1109/vtc2026-spring68026.2026.11757728}
}

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

  • small language models
  • edge computing
  • collaborative inference
  • query routing
  • uncertainty estimation
  • safety signals
  • privacy-preserving deployment

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?

Dahshan, M. H., Mamun, Q., & Debnath, T. (2026). SWARM-LLM: Collaborative Inference for Edge-based Small Language Models. IEEE Vehicular Technology Conference, 1–8. https://doi.org/10.1109/vtc2026-spring68026.2026.11757728

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 IEEE Vehicular Technology Conference: sign in and open the full text from this page.

Who wrote this paper?

Mostafa H. Dahshan, Quazi Mamun, Tanmoy Debnath.

What is the DOI of this paper?

10.1109/vtc2026-spring68026.2026.11757728, permanently at https://doi.org/10.1109/vtc2026-spring68026.2026.11757728. 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.