System One Models for Wireless Decision-Making:Applications and Performance Evaluation

2026-10-03

AI Summary

This study addresses the high latency and difficulty of adapting large language models (LLMs) to bounded decision spaces in wireless control. To overcome these limitations, this work proposes a lightweight alternative architecture based on System-One reasoning. By leveraging Jev for probabilistic distribution learning, the proposed framework directly models decision distributions over bounded control spaces, elucidating the inherent trade-off between decision quality and inference latency. Experimental evaluations on radio access network (RAN) slicing tasks demonstrate that the proposed method reduces latency by 3.5× while preserving utility, significantly outperforming both LLM-based and conventional baselines. These results validate its potential as an effective low-latency decision-making interface for wireless networks.

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.

Problem

• Wireless decision-making
• System-One models
• Latency constraints
• Bounded control problems
• Quality-latency tradeoff

Innovation

• System-One models
• Wireless decision-making
• Large language models
• Latency-quality tradeoff
• Intent-driven control