Back to AI News
arxiv

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.

AI Brief

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.

arXiv:2611.14211v1 Announce Type: cross Abstract: Software agents built on large language models generate traffic unlike human web traffic, yet routers have no class for it and cannot verify a sender's claim to be an agent. This paper proposes the Verifiable Agentic Traffic Class (VATC), which combines a reserved Differentiated Services Code Point (DSCP) value declaring agent traffic, a router-side classifier that demotes flows contradicting the declaration to a class served after best-effort traffic, and a rate-limited priority queue. VATC was compared with static Differentiated Services (DiffServ), a dedicated class that trusts the marking, and fq_codel, a per-flow fair-queuing scheduler, in two simulators and on a real Linux kernel. VATC matched DiffServ under steady load. In a constructed burst it cut mean agent queuing delay by 98% relative to DiffServ in simulation (assuming an immediate verdict), at a 12% increase in human delay; most of the gain came from the separate class. Under a spoofed flood in the kernel, the rate limit held human latency 11 times below DiffServ's. Without verification, DiffServ and a tightly configured fq_codel gave legitimate agents lower latency than VATC; a live four-feature classifier then demoted all 20 bulk-shaped spoofers and gave agents 0.30 ms, but missed six spoofers that copied the agent pattern. With emulated network delay, a timing feature of the classifier stopped separating agent from human flows. In real agent harnesses on a congested link, router queueing took 13% to 63% of task time, depending on harness and assumed model latency. The traffic was synthetic or sandbox-scale.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!