RIDAS: A Multi-Agent Framework for AI-RAN with Representation- and Intention-Driven Agents

TL;DR

RIDAS is a multi-agent framework that leverages large language models to translate user intents into optimal configurations for AI-enabled radio access networks, improving user capacity and resource efficiency.

Contribution

The paper introduces RIDAS, a novel multi-agent framework combining representation-driven and intention-driven agents with LLMs for AI RAN optimization.

Findings

Supports 36.47% more users than WirelessAgent under same QoS.

Efficiently maps user intents to network configurations.

Demonstrates improved resource allocation in AI RAN environments.

Abstract

Sixth generation (6G) networks demand tight integration of artificial intelligence (AI) into radio access networks (RANs) to meet stringent quality of service (QoS) and resource efficiency requirements. Existing solutions struggle to bridge the gap between high level user intents and the low level, parameterized configurations required for optimal performance. To address this challenge, we propose RIDAS, a multi agent framework composed of representation driven agents (RDAs) and an intention driven agent (IDA). RDAs expose open interface with tunable control parameters (rank and quantization bits, enabling explicit trade) offs between distortion and transmission rate. The IDA employs a two stage planning scheme (bandwidth pre allocation and reallocation) driven by a large language model (LLM) to map user intents and system state into optimal RDA configurations. Experiments demonstrate that RIDAS supports 36.47% more users than WirelessAgent under equivalent QoS constraints. These results validate ability of RIDAS to capture user intent and allocate resources more efficiently in AI RAN environments.