Contract-based Agentic Intent Framework for Network Slicing in O-RAN

TL;DR

This paper introduces a Contract-based Agentic Intent Framework (CAIF) for O-RAN that enhances network slicing safety by auditing user intents against formal constraints before actuation, validated on a testbed.

Contribution

It proposes a novel closed-loop agentic pipeline that decouples intent extraction from policy enforcement to ensure deterministic safety guarantees in network slicing.

Findings

Effectively eliminates harmful intent executions in tests

Demonstrates improved safety over baseline approaches

Validates approach on an O-RAN testbed

Abstract

Intent-based networking aims to simplify network operation by translating operator intents into a collection of policies, configurations, and control actions. However, this translation process relies on heuristics and loose coupling. It often results in unpredictable behavior and ambiguous safety standards. This paper presents a Contract-based Agentic Intent Framework (CAIF) for the radio access network (RAN). The proposed framework employs a closed-loop agentic pipeline that systematically audits user objectives against formal RAN constraints prior to actuation. The proposed CAIF decouples probabilistic intent extraction from strictly governed policy execution to enable the enforcement of deterministic safety guarantees. We use network slicing as a representative use case to demonstrate the design flow and validate the effectiveness of the proposed approach on an O-RAN testbed. Experimental results show that the closed-loop agentic pipeline of the proposed CAIF can effectively eliminate harmful intent executions observed in direct-actuation baseline approaches.