China Mobile Existing agent registration and discovery mechanisms assume that each intelligent agent is backed by a single, static inference model. However, in real-world deployments, agents increasingly incorporate internal model routing mechanisms where multiple foundation models are used dynamically within a single agent based on task complexity, latency requirements, system load, and cost constraints. Although such agents are exposed externally as single service endpoints, their execution behavior is not static and may vary due to internal model selection logic that is not visible to external systems. This leads to mismatches between registered metadata and actual service behavior, reducing the effectiveness of discovery and QoS-aware routing.