Wireless Personal Agent: Extending Wireless Intelligence from Networks to Terminals

2026-06-22

AI Summary

This work addresses the limitation of existing wireless intelligence approaches that focus predominantly on network-side performance while overlooking users’ personalized experience requirements shaped by application context, mobility patterns, cost sensitivity, privacy preferences, and long-term behavioral dynamics. To bridge this gap, we propose WISPA—a novel framework that, for the first time, deploys a large language model–driven self-evolving agent on the user device. By decoupling online execution from offline reflection, WISPA enables lightweight, interpretable resource allocation decisions and continuous adaptation of user preferences. The framework supports user-aware personalized connectivity strategies and facilitates long-term preference evolution learning. Experimental results in a campus commuting scenario demonstrate that WISPA effectively learns individualized connection styles and dynamically adjusts access decisions, significantly enhancing personalized user experience.

Abstract

Wireless networks are evolving from connectivity-oriented infrastructures into intelligent and personalized service platforms. Existing wireless intelligence remains centered on network-side optimization, improving objectives such as throughput, latency, and coverage. Nevertheless, besides network performance, wireless intelligence also depends on user-perceived experience via application context, mobility routine, service cost, privacy preference, and long-term usage behavior. This article proposes WISPA, a Wireless Intelligent Self-evolving Personal Agent framework for automated terminal-side resource management based on large language model (LLM)-based agent. To overcome the resource constraints on terminals, WISPA decouples the latency-sensitive online resource execution from offline LLM agent reflection. In this way, a lightweight online executor makes deterministic resource decisions using interpretable preference parameters; While an offline LLM agent analyzes terminal-side traces, refines user profiles, and updates online preference parameters for subsequent decisions. At last, we demonstrate the practical applicability and benefits of WISPA for terminal-side resource allocations on a campus commute route. Numerical results show that WISPA learns user-specific connection styles and adapts access decisions as preferences change.

Problem

• wireless intelligence
• personalized service
• user experience
• terminal-side resource management
• LLM-based agent

Innovation

• Wireless Personal Agent
• Large Language Model (LLM)
• Terminal-side Intelligence
• Self-evolving System
• Resource Management