Advanced AI Service Provisioning in O-RAN through LLM Engine Integration
For O-RAN operators, this proof-of-concept aims to automate AI service provisioning, but the work is incremental and lacks quantitative results.
The paper proposes a Dual-Brain architecture for O-RAN that uses an LLM-based orchestrator to translate operator intents into deployment code and data-collection policies, while a separate ML engine trains lightweight classifiers on demand, addressing the slow and manual process of creating AI xApps/rApps.
The Open Radio Access Network (O-RAN) architecture allows AI to be embedded directly into the RAN through modular xApps and rApps, yet creating these applications collecting data, training models, writing code, and deploying them safely remains slow and largely manual. Large Language Models (LLMs) offer strong reasoning and code-generation capabilities but are unsuited for the fast, deterministic inference required in real-time RAN control. We present a proof-of-concept Dual-Brain architecture that combines both strengths: an LLM-based orchestrator translates operator intents into data-collection policies and deployment code, while an automated ML engine, NeuralSmith, trains lightweight classifiers on demand via an API. We describe the architecture and provisioning workflow, share practical insights from a containerized O-RAN 5G~SA testbed, and discuss open research directions.