X-RIC improves network control with faster AI reasoning and lower costs
X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
Artificial IntelligenceHardware Architecture
Summary
Managing complex mobile networks can be challenging because current AI controllers don’t explain their decisions well and need a lot of training data. The authors designed X-RIC, a system that helps AI learn more efficiently by copying expert behaviors and using a special language model to interpret network conditions. Their approach also continuously improves itself based on feedback, making it faster and more reliable. This results in much lower operational costs while keeping network performance up to the required standards.
What this means in practice
- •For telecom network operators: Reduce the cost of managing network slices with faster, interpretable AI controllers that meet performance guarantees.
- •For telecom equipment vendors: Integrate X-RIC into O-RAN deployments to enable automated, agent-based control with improved training efficiency and explainability.$Commercial implications: Allows vendors to sell enhanced RIC modules with advanced AI reasoning that optimize network operations and reduce training complexities.
Authors
Adhwaa Al-Chaab, Ayman Younis, Dario Pompili
Abstract
The O-RAN ALLIANCE introduces architectural flexibility through disaggregation and AI-driven control. While the RAN Intelligent Controller (RIC) enables centralized optimization, current AI approaches lack reasoning capabilities and explainability. We propose eXplainable RIC (X-RIC), a novel framework integrating agentic AI into O-RAN architectures. X-RIC combines reactive Reinforcement Learning (RL) with strategic agentic reasoning through: (i) automated Behavioral Cloning (BC) using domain heuristics for sample-efficient training, (ii) a Telecom Language Model (TLM), a transformer-based reasoning module providing contextual abstraction and interpretability, and (iii) closed-loop co-adaptation within the Near-RT RIC control loop enabling continuous policy refinement. To ensure deployment readiness, we introduce BARX (Benchmarking Agentic Reasoning for RAN), a domain-specific evaluation framework assessing agentic control across latency, compliance, and determinism metrics. We validate X-RIC on SLA-aware network slicing in simulation and O-RAN-compliant testbed deployments. X-RIC achieves 89% operational cost reduction while maintaining SLA compliance, converging 75% faster with 50% fewer training steps and 46% lower variance.