System One models speed wireless control decisions with tradeoffs
System One Models for Wireless Decision-Making:Applications and Performance Evaluation
Artificial Intelligence
Summary
Wireless control systems often need to make quick, reliable choices from a limited set of options. The authors study System-One models, which directly learn probabilities for these choices instead of generating them step-by-step like large language models (LLMs). These models can make decisions much faster but sometimes with lower accuracy compared to specialized methods. Their tests show System-One models are especially good for time-sensitive wireless tasks, balancing speed and decision quality without fully replacing existing optimization methods.
What this means in practice
- •For network schedulers: Make faster resource and antenna selections in wireless networks by using System-One models that reduce response times while maintaining reasonable decision quality.
- •For cloud infrastructure operators: Improve intent-based network slicing decisions to accelerate management actions with System-One models offering latency improvements without utility loss.
Authors
Masoud Rahimi, S. M. Matin Alemohammad, Hamid Behroozi, Mahdi Nouri
Abstract
Many wireless control tasks require repeated selection of a single action from a finite feasible set under stringent latency and reliability constraints. While large language models (LLMs) have recently emerged as general-purpose decision engines, their autoregressive generation mechanism is not naturally aligned with such bounded control problems. This paper investigates System-One models, which directly learn probability distributions over explicitly defined decision spaces, as a lightweight alternative for wireless decision-making. We formalize their decision structure and learning objective, identify their applicability across physical-layer control, radio resource management, mobility, network slicing, and network operations, and evaluate their practical behavior through representative wireless case studies. Using Jev as a System-One implementation, we benchmark decision quality and client-observed latency against generative LLMs and conventional baselines. In receive-antenna selection, Jev delivers up to an 8.5x reduction in median response latency relative to the evaluated LLMs, although this gain comes with a loss in decision quality compared with stronger task-specific alternatives. More notably, in intent-conditioned RAN slicing, Jev achieves utility comparable to the evaluated LLMs while providing more than a 3.5x reduction in median response latency. Complementary evidence from edge-service orchestration further shows that faster decisions do not necessarily translate into lower end-to-end service latency. These results expose a fundamental quality/latency tradeoff and position System-One models not as replacements for numerical optimization, but as a promising decision interface for latency-sensitive, bounded, and intent-driven wireless control.