In Autonomous Network Levels 4-5, AI agents need to invoke tools across vendor boundaries without human oversight. However, existing management standards lack a standardized mechanism for cross-vendor trust visibility. When a tool from Vendor B is compromised, agents from Vendor A continue invoking it, unaware of the trust degradation, leading to cascading service impacts.
We present AgentToolMO, a proposed 3GPP NRM information model for agent tool trust management. The model includes:
- A formally defined trust state machine with provable graduated enforcement;
- Damped cascade propagation with bounded convergence;
- Cross-vendor trust notifications via existing Management Services (MnS) interfaces;
- Retroactive impact assessment through NRM dependency graph traversal.
Simulation-based evaluation across multi-vendor topologies shows that standardized cross-vendor notifications reduce the blast radius from hours-scale undetected propagation to near-real-time containment, bounded by MnS notification delivery, with cascade convergence guaranteed in bounded iterations and sub-linear notification scaling across vendor domains. The framework operates within existing 3GPP management infrastructure, leverages existing protocols, and provides a standardization pathway for trustworthy multi-vendor autonomous network management.
Blogger's Review: The proposed AgentToolMO model offers an innovative trust management solution for cross-vendor network management, significantly enhancing security and efficiency. Its standardized notification mechanism is crucial for the future development of autonomous networks, especially in diverse vendor environments, paving the way for more robust network operations.