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

2026-03-02

AI Summary

This work addresses the limitations of existing intent-driven networks, which rely on heuristic approaches and loosely coupled mechanisms that fail to ensure predictable and safe behavior. To overcome these challenges, the authors propose the Contract-based Agent Intent Framework (CAIF), introducing for the first time a formal contract mechanism into O-RAN. CAIF employs a closed-loop agent architecture that decouples probabilistic intent extraction from policy execution and performs systematic auditing of user objectives against RAN constraints prior to enforcement. By separating intent interpretation from policy implementation, the framework enables verifiable alignment between high-level intents and network actions. Experimental validation on an O-RAN testbed demonstrates its effectiveness in network slice management, significantly eliminating harmful operations, providing deterministic safety guarantees, and enhancing overall system reliability.

Technology Category

• Planning, Routing, and Scheduling: Plan Execution and Monitoring
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Mechanism Design

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

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.

Problem

• Intent-based Networking
• Network Slicing
• O-RAN
• Safety Guarantees
• RAN

Innovation

• Contract-based
• Agentic Intent
• Network Slicing
• O-RAN
• Closed-loop Pipeline