Telecom World Models: Unifying Digital Twins, Foundation Models, and Predictive Planning for 6G

2026-04-08

AI Summary

Current language models lack explicit modeling of network dynamics, while traditional digital twins struggle to support learning and decision-making under uncertainty, failing to meet the demands of 6G systems for multi-layer coordination, state evolution, and control-impact prediction. To address this, this work proposes the Telecom World Model (TWM), which innovatively integrates digital twin technology, foundation models, and predictive planning into a three-tier architecture comprising a field world model, a control/dynamics world model, and a telecom foundation model. This framework enables spatial environment forecasting, action-conditioned KPI trajectory prediction, and intent-driven orchestration. Experiments in network slicing scenarios demonstrate that the full TWM significantly outperforms single-world baselines, accurately predicting KPI trajectories and facilitating efficient, robust model-driven decision-making.

Abstract

The integration of machine learning tools into telecom networks, has led to two prevailing paradigms, namely, language-based systems, such as Large Language Models (LLMs), and physics-based systems, such as Digital Twins (DTs). While LLM-based approaches enable flexible interaction and automation, they lack explicit representations of network dynamics. DTs, in contrast, offer a high-fidelity network simulation, but remain scenario-specific and are not designed for learning or decision-making under uncertainty. This gap becomes critical for 6G systems, where decisions must take into account the evolving network states, uncertainty, and the cascading effects of control actions across multiple layers. In this article, we introduce the {Telecom World Model}~(TWM) concept, an architecture for learned, action-conditioned, uncertainty-aware modeling of telecom system dynamics. We decompose the problem into two interacting worlds, a controllable system world consisting of operator-configurable settings and an external world that captures propagation, mobility, traffic, and failures. We propose a three-layer architecture, comprising a field world model for spatial environment prediction, a control/dynamics world model for action-conditioned Key Performance Indicator (KPI) trajectory prediction, and a telecom foundation model layer for intent translation and orchestration. We showcase a comparative analysis between existing paradigms, which demonstrates that TWM jointly provides telecom state grounding, fast action-conditioned roll-outs, calibrated uncertainty, multi-timescale dynamics, model-based planning, and LLM-integrated guardrails. Furthermore, we present a proof-of-concept on network slicing to validate the proposed architecture, showing that the full three-layer pipeline outperforms single-world baselines and accurately predicts KPI trajectories.

Problem

• 6G
• Digital Twins
• Large Language Models
• Uncertainty
• Network Dynamics

Innovation

• Telecom World Model
• Digital Twins
• Foundation Models
• Action-Conditioned Prediction
• Uncertainty-Aware Planning