On-Device LLM for Context-Aware Wi-Fi Roaming

TL;DR

This paper presents a novel on-device large language model that enables context-aware Wi-Fi roaming decisions, improving stability and signal quality in mobile environments through cross-layer reasoning and optimized edge deployment.

Contribution

It introduces the first use of an on-device LLM for Wi-Fi roaming, combining high-level reasoning with cross-layer control and optimization techniques for real-time edge deployment.

Findings

Outperforms legacy heuristics and DRL baselines in experiments

Achieves a balance between roaming stability and signal quality

Demonstrates feasibility of on-device LLM for wireless control

Abstract

Roaming in Wireless LAN (Wi-Fi) is a critical yet challenging task for maintaining seamless connectivity in dynamic mobile environments. Conventional threshold-based or heuristic schemes often fail, leading to either sticky or excessive handovers. We introduce the first cross-layer use of an on-device large language model (LLM): high-level reasoning in the application layer that issues real-time actions executed in the PHY/MAC stack. The LLM addresses two tasks: (i) context-aware AP selection, where structured prompts fuse environmental cues (e.g., location, time) to choose the best BSSID; and (ii) dynamic threshold adjustment, where the model adaptively decides when to roam. To satisfy the tight latency and resource budgets of edge hardware, we apply a suite of optimizations-chain-of-thought prompting, parameter-efficient fine-tuning, and quantization. Experiments on indoor and outdoor datasets show that our approach surpasses legacy heuristics and DRL baselines, achieving a strong balance between roaming stability and signal quality. These findings underscore the promise of application-layer LLM reasoning for lower-layer wireless control in future edge systems.