BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks

TL;DR

This paper introduces BRAIN, a Bayesian active inference agent for 6G networks that improves adaptability, explainability, and robustness over traditional deep reinforcement learning methods, enabling real-time decision-making and transparent reasoning.

Contribution

The paper presents BRAIN, a novel Bayesian reasoning framework for network agents that unifies perception and action, demonstrating superior adaptability and interpretability in dynamic environments.

Findings

BRAIN maintains QoS targets under varying traffic loads.

It shows 28.3% higher robustness to traffic shifts without retraining.

BRAIN provides human-interpretable belief diagnostics for decisions.

Abstract

Future sixth-generation (6G) mobile networks will demand artificial intelligence (AI) agents that are not only autonomous and efficient, but also capable of real-time adaptation in dynamic environments and transparent in their decisionmaking. However, prevailing agentic AI approaches in networking, exhibit significant shortcomings in this regard. Conventional deep reinforcement learning (DRL)-based agents lack explainability and often suffer from brittle adaptation, including catastrophic forgetting of past knowledge under non-stationary conditions. In this paper, we propose an alternative solution for these challenges: Bayesian reasoning via Active Inference (BRAIN) agent. BRAIN harnesses a deep generative model of the network environment and minimizes variational free energy to unify perception and action in a single closed-loop paradigm. We implement BRAIN as O-RAN eXtended application (xApp) on GPU-accelerated testbed and demonstrate its advantages over standard DRL baselines. In our experiments, BRAIN exhibits (i) robust causal reasoning for dynamic radio resource allocation, maintaining slice-specific quality of service (QoS) targets (throughput, latency, reliability) under varying traffic loads, (ii) superior adaptability with up to 28.3% higher robustness to sudden traffic shifts versus benchmarks (achieved without any retraining), and (iii) real-time interpretability of its decisions through human-interpretable belief state diagnostics.