Autonomous AI agents stabilized for shared O-RAN radio control
Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN
Networking and Internet ArchitectureArtificial Intelligence
Summary
Managing radio resources in O-RAN with independent AI agents can cause problems when their goals conflict. The authors show that two agents trying to optimize different objectives cause unstable resource sharing that harms the system. They created AURA, a system that carefully allows agent actions only if they keep things stable, proven to converge to a workable solution. Testing on a real setup, AURA greatly reduced resource conflicts and avoided performance drops for users.
What this means in practice
- •For wireless network operators: Avoid recurring resource conflicts when multiple AI agents control shared radio network slices in O-RAN environments.
- •For telecommunications platform developers: Integrate an arbitration layer that guarantees stable multi-agent radio resource management in O-RAN testbeds and implementations.
Authors
Seyed Bagher Hashemi Natanzi, Bo Tang
Abstract
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.