PapersSelected

Stability-Guaranteed Arbitration for Autonomous AI Agents in O-RAN

Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN

Why we picked it

For those working with or studying the O-RAN architecture, this paper provides a concrete solution to a critical safety problem involving autonomous AI agents.

This paper presents AURA, a lightweight arbitration layer for the O-RAN control plane.

Body

It addresses the safety issue of autonomous AI agents independently managing shared radio resources.AURA ensures agent actions are feasible and proves the system converges to a stable operating point.

Implemented on an OpenAirInterface testbed, AURA reduced shared resource excursions by over an order of magnitude and eliminated cross-slice throughput starvation.

Original · arXiv cs.AI

Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN

The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources. We demonstrate on a live O-RAN system that this independence is unsafe. Two agents with individually correct objectives, one protecting a latency SLA and one maximizing utilization for energy efficiency, jointly drive recurring opposing excursions of the shared resource partition that neither produces alone. Existing conflict-mitigation mechanisms presume a statically known application population and cannot govern agents whose behavior emerges at run time. We present AURA, a lightweight arbitration layer that admits agent actions only when they satisfy feasibility invariants, per-variable dwell times, and a deadband, and we prove the arbitrated system converges to a feasible operating point. Implemented on an OpenAirInterface (OAI) testbed with measured one-way latency and throughput, AURA reduces recurring shared-state excursions by more than an order of magnitude (from 8.4 to 0.4 PRB amplitude) and virtually eliminates cross-slice throughput starvation (from 40-55% to 0.3%), while leaving the protected slice's own latency compliance unchanged, a trade-off the convergence guarantee makes explicit.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include O-RAN, agents.

Source attribution: curated from arXiv cs.AI (@Seyed Bagher Hashemi Natanzi, Bo Tang).