AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular Networks

TL;DR

AURA combines cloud-based LLMs for high-level planning with MARL agents for local decisions in NextG networks, improving resilience and reducing failures while managing latency and scalability challenges.

Contribution

This paper introduces AURA, a novel framework integrating LLMs with MARL for scalable, real-time NextG network management, balancing high-level reasoning with local adaptability.

Findings

Reduces dropped handoff requests by over 50% in simulations.

Agents use LLM guidance in fewer than 60% of decisions, showing effective augmentation.

Improves network resilience and reduces system failures under high traffic.

Abstract

Next-generation (NextG) cellular networks are expected to manage dynamic traffic while sustaining high performance. Large language models (LLMs) provide strategic reasoning for 6G planning, but their computational cost and latency limit real-time use. Multi-agent reinforcement learning (MARL) supports localized adaptation, yet coordination at scale remains challenging. We present AURA, a framework that integrates cloud-based LLMs for high-level planning with base stations modeled as MARL agents for local decision-making. The LLM generates objectives and subgoals from its understanding of the environment and reasoning capabilities, while agents at base stations execute these objectives autonomously, guided by a trust mechanism that balances local learning with external input. To reduce latency, AURA employs batched communication so that agents update the LLM's view of the environment and receive improved feedback. In a simulated 6G scenario, AURA improves resilience, reducing dropped handoff requests by more than half under normal and high traffic and lowering system failures. Agents use LLM input in fewer than 60\% of cases, showing that guidance augments rather than replaces local adaptability, thereby mitigating latency and hallucination risks. These results highlight the promise of combining LLM reasoning with MARL adaptability for scalable, real-time NextG network management.