Multi-Agentic AI for Conflict-Aware rApp Policy Orchestration in Open RAN

TL;DR

This paper introduces a multi-agent AI framework utilizing large language models to automate and enhance rApp policy generation and orchestration in Open RAN, significantly improving deployment accuracy and reducing reasoning costs.

Contribution

It presents a novel multi-agent AI architecture with LLM-based agents for conflict-aware rApp policy orchestration in Open RAN, enabling scalable and autonomous network management.

Findings

Achieves over 70% improvement in deployment accuracy.

Reduces reasoning cost by 95%.

Maintains zero-shot generalization to unseen intents.

Abstract

Open Radio Access Network (RAN) enables flexible, AI-driven control of mobile networks through disaggregated, multi-vendor components. In this architecture, xApps handle real-time functions, whereas rApps in the non-real-time controller generate strategic policies. However, current rApp development remains largely manual, brittle, and poorly scalable as xApp diversity proliferates. In this work, we propose a Multi-Agentic AI framework to automate rApp policy generation and orchestration. The architecture integrates three specialized large language model (LLM)-based agents, Perception, Reasoning, and Refinement, supported by retrieval-augmented generation (RAG) and memory-based analogical reasoning. These agents collectively analyze potential conflicts, synthesize intent-aligned control pipelines, and incrementally refine deployment decisions. Experiments across diverse deployment scenarios demonstrate that the proposed system achieves over 70% improvement in deployment accuracy and 95% reduction in reasoning cost compared to baseline methods, while maintaining zero-shot generalization to unseen intents. These results establish a scalable and conflict-aware solution for fully autonomous, zero-touch rApp orchestration in Open RAN.