A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network
IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 3815-3830
DOI: 10.1109/tccn.2025.3620286 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Haoxiang Luo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Major Key Project of PCL.
Abstract (Originalsprache)
Large Language Models (LLMs) have achieved remarkable success across a wide range of applications. However, individual LLMs often produce inconsistent, biased, or hallucinated outputs due to limitations in their training corpora and model architectures. Recently, collaborative frameworks such as the Multi-LLM Network (MultiLLMN) have been introduced, enabling multiple LLMs to interact and jointly respond to user queries. Nevertheless, MultiLLMN architectures raise critical concerns regarding the reliability and security of the generated content, particularly in open environments where malicious or compromised LLMs may be present. Moreover, reliance on centralized coordination undermines system efficiency and introduces single points of failure. In this paper, we propose a novel Trusted MultiLLMN framework, driven by a Weighted Byzantine Fault Tolerance (WBFT) blockchain consensus mechanism, to ensure the reliability, security, and efficiency of multi-LLM collaboration. In WBFT, voting weights are adaptively assigned to each LLM based on its response quality and trustworthiness, incentivizing reliable behavior, and reducing the impact of malicious nodes. Extensive simulations demonstrate that WBFT significantly improves both consensus security and efficiency compared to classical and modern consensus mechanisms, particularly under wireless network conditions. Furthermore, our evaluations reveal that Trusted MultiLLMN supported by WBFT can deliver higher-quality and more credible responses than both single LLMs and conventional MultiLLMNs, thereby providing a promising path toward building robust, decentralized AI collaboration networks.
Förderung
- Major Key Project of PCL
Zitieren
APA
Luo, H., Sun, G., Liu, Y., Zhao, D., Niyato, D., Yu, H., & Dustdar, S. (2026). A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network. IEEE Transactions on Cognitive Communications and Networking, 12, 3815-3830. https://doi.org/10.1109/tccn.2025.3620286
Vancouver
Luo H, Sun G, Liu Y, Zhao D, Niyato D, Yu H, et al. A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network. IEEE Transactions on Cognitive Communications and Networking. 2026;12:3815-3830. doi:10.1109/tccn.2025.3620286
BibTeX
@article{Luo2026,
author = {Luo, Haoxiang and Sun, Gang and Liu, Yinqiu and Zhao, Dongcheng and Niyato, Dusit and Yu, Hongfang and Dustdar, Schahram},
title = {A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network},
journal = {IEEE Transactions on Cognitive Communications and Networking},
year = {2026},
volume = {12},
pages = {3815--3830},
doi = {10.1109/tccn.2025.3620286}
}
EUVIMED