Against the Monolithic Wireless World Model: Why NextG Needs Composable and Agentic Intelligence

2026-05-15

AI Summary

This work addresses the lack of a self-contained, reusable data foundation in wireless communication, which hinders the deployment of monolithic AI models in AI-native networks. To overcome this limitation, the paper proposes a modular, embodied intelligence architecture centered around a general-purpose reasoning model. This core coordinates with specialized signal processing models, classical wireless algorithms, digital twins, and standardized perception-retrieval components through explicit, programmable interfaces. By departing from conventional large-model paradigms and aligning with the inherent structural properties of wireless data, the proposed framework offers a more feasible and deployable AI-native architecture for NextG networks. It effectively circumvents fundamental bottlenecks faced by existing wireless world models in terms of data grounding and task generalization.

Abstract

AI-native 6G visions increasingly invoke wireless foundation models, large multimodal models, and wireless world models as the natural endpoint of AI-native networking, drawing an analogy to recent developments in large language models (LLMs). We argue that this analogy is structurally incomplete. The success of LLMs is based on a broad, reusable, and largely self-contained tokenized data substrate, whereas the wireless domain lacks an equivalent data foundation. Unlike text, code, or images, wireless data such as CSI tensors, IQ samples, or scheduler logs are not self-contained: their meaning is configuration-dependent, simulator-conditioned, task-disaggregated, and weakly grounded in operational feedback, all structural bottlenecks that undermine current pre- and post-training recipes. We therefore argue that monolithic models, including mixture-of-experts (MoE) and wireless world models, are not the most realistic near-term path toward deployable AI-native networks. Instead, emerging evidence points toward composable and agentic network architectures, where general reasoning models orchestrate specialized signal processing models, classical algorithms, digital twins, standards-aware retrieval, and safety checks through explicit programmable interfaces.

Problem

• monolithic wireless world model
• AI-native networking
• wireless data foundation
• composable intelligence
• agentic architecture

Innovation

• composable intelligence
• agentic networks
• wireless foundation models
• AI-native networking
• programmable interfaces