arXiv：cs.AI· Haowen Wan, Shangzhuo Xie, Syue-Ju Syue, Xianyue Wu, Runhua Li, Qianqian Yang·· 16 小时前
PEAM：面向个性化、高效、自主移动网络配置的端侧通信智能体
PEAM: On-device Communication Agent for Personalized, Efficient and Autonomous Mobile Network Configuration
AI 导读
PEAM 是一款基于端侧 LLM 的通信智能体，能在毫秒内自主生成个性化网络配置规则。它先用人工标注的真实用户数据微调端侧 LLM，再分规则生成（设备空闲时分批分析历史配置记录并构建用户画像）与规则执行两阶段运行。基于微调后的 4B 模型，PEAM 的网络配置决策正确率达 99.13%，生成规则有效率 92.50%，分别比传统专家规则方法高出 4.41% 和 84.50%。
正文
Abstract:The growing deployment of compact large language models on smartphones is enabling autonomous on-device decision-making, such as emerging mobile GUI agents. However, many mobile decisions, such as network configuration when users switch apps or connectivity conditions change, must satisfy stringent latency constraints to preserve user experience. In this paper, we propose PEAM, an on-device LLM-based communication agent that autonomously generates personalized network-configuration rules executable within milliseconds. Specifically, PEAM first fine-tune the on-device LLM with a dataset constructed from manually annotated real-user data to integrate the communication knowledge into the local model. PEAM then operates in two phases. In the rule-generation phase, which is performed when the device is idle, such as overnight, PEAM analyzes historical network-configuration records in batches and reflects across batches to consolidate consistent evidence, reduce local bias, and derive robust configuration rules. To enable more accurate and stable rule generation over time, PEAM further constructs a user profile from high-confidence rules to capture the user's network preferences and incorporates this profile into each rule-generation cycle. In the rule-execution phase, PEAM is invoked when the communication context changes, such as when users switch apps or connectivity conditions change, and searches the rule library to identify and execute the appropriate rule. Experiments demonstrate that PEAM, based on a fine-tuned 4B model, achieves 99.13% correct network configuration decisions, while 92.50% of the rules generated by PEAM are valid, outperforming the traditional expert-rule based method by 4.41% and 84.50%, respectively.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14855 [cs.AI] |
| (or arXiv:2610.14855v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14855 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haowen Wan [view email]
[v1]
Sat, 10 Oct 2026 12:21:05 UTC (4,753 KB)
来源：arXiv：cs.AI · arxiv.org