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

2025-07-17

AI Summary

To bridge the semantic gap between high-level user intents and low-level resource configuration in AI-integrated Radio Access Networks (AI-RAN) for 6G, this paper proposes RIDAS—a multi-agent framework comprising a representation-driven agent and an intent-driven agent operating in synergy. RIDAS innovatively incorporates a large language model (LLM)-guided two-stage bandwidth planning mechanism to achieve precise intent-to-parameter mapping. The framework integrates tunable-rank/quantized-bit interfaces, proactive bandwidth pre-allocation, and dynamic reallocation mechanisms. Experimental results demonstrate that, under identical QoS constraints, RIDAS supports 44.71% more users than WirelessAgent, while significantly improving intent comprehension accuracy and spectral resource utilization efficiency.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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 44.71% 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.

Problem

• Bridging high-level user intents and low-level RAN configurations
• Optimizing QoS and resource efficiency in 6G AI-RAN
• Enhancing user capacity under strict QoS constraints

Innovation

• Multi-agent framework with RDAs and IDA
• LLM-driven two-stage planning scheme
• Tunable control parameters for trade-offs