Skip to content

Enhanced SageAttention2-Based GNNs for Reliable Block Propagation Optimization in Blockchain-Enabled Internet of Agents

2026 · IEEE Transactions on Network Science and Engineering · Vol 13, pp. 11853-11868 · 0 citations · 82 references

Abstract

Internet of Agents (IoA) is an emerging paradigm in which autonomous Artificial Intelligence (AI) agents collaborate across organizational boundaries. Since distributed agent interactions lack a pre-established trusted central authority, blockchain, as a decentralized technology, can be integrated into IoA for decentralized and tamper-proof trust management, where service interaction records among agents are recorded into blocks through reliable consensus mechanisms. However, inefficient block propagation during the consensus process can cause redundant and outdated information. Moreover, existing block propagation schemes cannot handle dynamic block sizes caused by varying AI agent workloads or detect strategic attacks, where malicious miners strategically alternate between honest and malicious behaviors. To this end, in this paper, we propose a reliable block propagation optimization framework for public blockchain-enabled IoA. Specifically, we first design a metric called Dynamic Age of Block (DAoB) to measure block freshness under heterogeneous AI agent workloads. Then, we propose a four-element subjective logic model that incorporates behavioral volatility into ternary subjective logic models to rapidly detect changes in miner behavior. Furthermore, we develop an enhanced SageAttention2-based Graph Neural Network (GNN) model, in which quantized attention is adapted from parallel inference to sequential reinforcement learning, thereby facilitating efficient and reliable block propagation optimization. Numerical results demonstrate that the proposed model outperforms baseline methods, achieves up to 84.8% memory reduction compared with standard graph attention, and achieves an average 36% reduction in DAoB-based block propagation latency under low-bandwidth conditions compared with the gossip protocol.

View source

Similar papers

2026

Toward Trustworthy Coordination in Intelligent Edge Agent Networking: A Trust-Driven Transaction Propagation Mechanism

Intelligent edge networks increasingly use blockchain to support trustworthy collaboration among distributed autonomous edge agents. However, dynamic and heterogeneous edge environments expose intelligent edge agents to spam transaction attacks, where adversaries exploit repeated per-hop verification to exhaust limited...

Xi-Jia Lu, Xing-Wei Wang, Qiang He et al. · 0 citations
2026

TCAA: An Efficient Blockchain Consensus Based on Transaction Collector and Address Aggregation for UAV Ad Hoc Networks

Blockchain technology provides a promising solution to data security and trust challenges in uncrewed aerial vehicle (UAV) ad hoc networks. However, conventional consensus mechanisms suffer from notable inefficiencies in resource-constrained environments, characterized by high computational and communication overhead,...

Wei Zhang, Shi-Yun Xiong, Yi-Xin Li et al. · 0 citations
2026

HashVer: Low-Latency Consensus on Blockchain Networks With Heterogeneous Nodes

Blockchain can enhance the security of networks and enable high-quality collaborations among distributed nodes. But meanwhile, its consensus process introduces additional message interactions and verifications into the network. The resource-constrained nodes create bottlenecks in the multi-hop message propagation and r...

Yi-Xin Li, Yan Lei, Xiao-Jie Peng et al. · 0 citations
Open access Nov 2026

Blockchain Intelligence-Based Trust Management System for Internet of Vehicles

The Internet of Vehicles (IoV) extends automotive systems through vehicle-to-everything (V2X) communication, creating a collaborative ecosystem to enhance transportation efficiency and road safety. However, the decentralized and open vehicular network is vulnerable to internal malicious participants that disseminate fa...

Zhi-Peng Wang, Rafidah Md. Noor, K. Sadakane et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.