Computer Science editorial
Open AccessOA2026
Wireless Personal Agent: Extending Wireless Intelligence from Networks to Terminals
A digest of WISPA: an LLM-based self-evolving personal agent for terminal-side resource management
Jiedan Tan; Fang Liu; Jingwen Tong; Shengli Zhang; Jun Zhang; Wing Shing Wongยท 2026ยท DOI 10.48550/arXiv.2606.23255
The core problem
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. However, 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 a large language model (LLM)-based agent. The core motivation is to extend wireless intelligence from the network to the terminal, where personalized, context-aware decisions can be made.
Innovation
The authors 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. While specific quantitative metrics are not detailed in the abstract, the results indicate that the framework successfully captures and responds to individual user behavior over time.
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. However, 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 a large language model (LLM)-based agent. The core motivation is to extend wireless intelligence from the network to the terminal, where personalized, context-aware decisions can be made.
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. The online executor can be formulated as a deterministic policy that selects an access decision at time based on a preference parameter vector and current context :
Why it matters
WISPA represents a shift from network-centric to user-centric wireless intelligence. By leveraging LLM-based agents for offline reflection and lightweight online execution, it addresses the resource constraints of terminals while enabling personalized, self-evolving resource management. The decoupled architecture allows for interpretable online decisions and continuous adaptation to changing user preferences. This approach has implications for future wireless systems where user experience, privacy, and cost preferences are paramount. The taxonomy candidates of Architecture, Cybersecurity, Network, and Cryptography suggest potential intersections with secure and efficient terminal-side operations.
Who should read this
CS practitioners and researchers
Opening member contentโฆ