![[2602.16738] Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.16738] Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance
Summary
The paper presents SEMAS, a self-evolving multi-agent network designed for predictive maintenance in Industrial IoT, enhancing real-time anomaly detection while maintaining interpretability and efficiency.
Why It Matters
As industries increasingly adopt IoT technologies, the need for efficient predictive maintenance systems is critical. SEMAS addresses the limitations of traditional models by offering a dynamic, resource-aware solution that adapts to changing operational conditions, thus improving reliability and performance in industrial applications.
Key Takeaways
- SEMAS utilizes a hierarchical multi-agent architecture for enhanced anomaly detection.
- The system operates across Edge, Fog, and Cloud tiers to optimize resource use.
- Proximal Policy Optimization (PPO) is employed for continuous policy improvement.
- Empirical results show SEMAS outperforms traditional methods in stability and latency.
- The framework supports real-time deployment without sacrificing interpretability.
Computer Science > Multiagent Systems arXiv:2602.16738 (cs) [Submitted on 17 Feb 2026] Title:Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance Authors:Rebin Saleh, Khanh Pham Dinh, Balázs Villányi, Truong-Son Hy View a PDF of the paper titled Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance, by Rebin Saleh and 3 other authors View PDF HTML (experimental) Abstract:Industrial IoT predictive maintenance requires systems capable of real-time anomaly detection without sacrificing interpretability or demanding excessive computational resources. Traditional approaches rely on static, offline-trained models that cannot adapt to evolving operational conditions, while LLM-based monolithic systems demand prohibitive memory and latency, rendering them impractical for on-site edge deployment. We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge, Fog, and Cloud computational tiers. Edge agents perform lightweight feature extraction and pre-filtering; Fog agents execute diversified ensemble detection with dynamic consensus voting; and Cloud agents continuously optimize system policies via Proximal Policy Optimization (PPO) while maintaining asynchronous, non-blocking inference. The framework incorporates LLM-based response generation for explainability and federated knowledge aggregation for adaptive policy distribution. This architecture enables resource-aware specializati...
