SORA-ATMAS: Adaptive Trust Management and Multi-LLM Aligned Governance for Future Smart Cities

TL;DR

SORA-ATMAS integrates decentralized agentic AI with centralized governance using a dual-chain architecture to address GRC challenges in future smart cities. By formalizing adaptive trust and risk through standardized metrics and MAE-driven LLM evaluation, the framework guides multiple domain agents (Weather, Traffic, Safety) toward policy-aligned outputs while preserving edge autonomy. Empirical results show a ~$35\%$ reduction in MAE across agents and practical runtime performance (throughput $13.8$–$17.2$ req/s, per-request time $58$–$72$ ms, governance delay $21$–$92$ ms), indicating real-time, cross-domain interoperability with strong provenance via blockchain anchoring. The work demonstrates that a hybrid GRC approach—centralized oversight with decentralized, context-aware execution—can provide a scalable, privacy-preserving, and auditable foundation for resilient smart-city management.

Abstract

The rapid evolution of smart cities has increased the reliance on intelligent interconnected services to optimize infrastructure, resources, and citizen well-being. Agentic AI has emerged as a key enabler by supporting autonomous decision-making and adaptive coordination, allowing urban systems to respond in real time to dynamic conditions. Its benefits are evident in areas such as transportation, where the integration of traffic data, weather forecasts, and safety sensors enables dynamic rerouting and a faster response to hazards. However, its deployment across heterogeneous smart city ecosystems raises critical governance, risk, and compliance (GRC) challenges, including accountability, data privacy, and regulatory alignment within decentralized infrastructures. Evaluation of SORA-ATMAS with three domain agents (Weather, Traffic, and Safety) demonstrated that its governance policies, including a fallback mechanism for high-risk scenarios, effectively steer multiple LLMs (GPT, Grok, DeepSeek) towards domain-optimized, policy-aligned outputs, producing an average MAE reduction of 35% across agents. Results showed stable weather monitoring, effective handling of high-risk traffic plateaus 0.85, and adaptive trust regulation in Safety/Fire scenarios 0.65. Runtime profiling of a 3-agent deployment confirmed scalability, with throughput between 13.8-17.2 requests per second, execution times below 72~ms, and governance delays under 100 ms, analytical projections suggest maintained performance at larger scales. Cross-domain rules ensured safe interoperability, with traffic rerouting permitted only under validated weather conditions. These findings validate SORA-ATMAS as a regulation-aligned, context-aware, and verifiable governance framework that consolidates distributed agent outputs into accountable, real-time decisions, offering a resilient foundation for smart-city management.

Figures (11)

• Figure 1: AI-based smart-city ecosystem illustrating agentic service agents and repositories supervised by a dynamic security governance pipeline: security process → risk analysis → compliance, which coordinates cross-domain services via inter-agent links.
• Figure 2: Layered SDIoT-based governance framework integrating the SORA Governance Layer and Agentic Layer within the Application Layer.
• Figure 3: Proposed governance framework integrating decentralized AI agents, Agentic Blockchain, and the SORA Governance Layer over the SORA Blockchain, enabling adaptive trust and cross-domain policy enforcement.
• Figure 4: 20-hour temperature and weather regime forecast (Islamabad example). The line graph shows predicted temperature trends with overlaid regime labels (Normal/Rain), which are used by the Weather Agent’s trust and risk computations..
• Figure 5: YOLOv8 traffic-density output with bounding boxes and confidence scores. Aggregated counts feed directly into the Traffic Agent’s risk-trust pipeline.