Verifiable Agentic Traffic Class for AI Agent QoS
The paper proposes Verifiable Agentic Traffic Class (VATC), which combines a reserved DSCP declaration for agent traffic, a router-side classifier that demotes flows contradicting the declaration, and a rate-limited priority queue. VATC was compared with static DiffServ and fq_codel in two simulators and on a real Linux kernel. In a constructed burst simulation assuming an immediate verdict, VATC cut mean agent queuing delay by 98% relative to DiffServ while increasing human delay by 12%; under a spoofed flood in the kernel, its rate limit held human latency 11 times below DiffServ's. The authors report caveats: without verification, DiffServ and tightly configured fq_codel gave legitimate agents lower latency, and a live four-feature classifier missed six spoofers that copied the agent pattern; traffic was synthetic or sandbox-scale.
It introduces and adversarially evaluates a concrete QoS mechanism for distinguishing and scheduling agentic AI traffic, with results relevant to network operators and agent-system builders.
Comments & Questions (0)
No comments yet
Be the first to comment!