PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power Management

2026-03-19

AI Summary

This work addresses the inefficiency of existing mobile power management approaches, which rely on static rules and lack awareness of user context and preferences. To overcome this limitation, the study introduces large language models (LLMs) into zero-shot, context-aware power management on mobile devices for the first time, proposing a multi-agent architecture that interprets UI semantics to recognize user activities. The system automatically generates safe, personalized power policies covering 18 configuration parameters by integrating PDL-based constraint validation and a two-tier memory mechanism grounded in confidence-aware distillation. Evaluated on real Android devices, the approach incurs only 0.5% daily battery overhead while achieving 81.7% action prediction accuracy and reducing energy consumption by 38.8%. User preferences converge rapidly within 3–5 days, substantially outperforming current baselines.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Battery life remains a critical challenge for mobile devices, yet existing power management mechanisms rely on static rules or coarse-grained heuristics that ignore user activities and personal preferences. We present PowerLens, a system that tames the reasoning power of Large Language Models (LLMs) for safe and personalized mobile power management on Android devices. The key idea is that LLMs' commonsense reasoning can bridge the semantic gap between user activities and system parameters, enabling zero-shot, context-aware policy generation that adapts to individual preferences through implicit feedback. PowerLens employs a multi-agent architecture that recognizes user context from UI semantics and generates holistic power policies across 18 device parameters. A PDL-based constraint framework verifies every action before execution, while a two-tier memory system learns individualized preferences from implicit user overrides through confidence-based distillation, requiring no explicit configuration and converging within 3--5 days. Extensive experiments on a rooted Android device show that PowerLens achieves 81.7% action accuracy and 38.8% energy saving over stock Android, outperforming rule-based and LLM-based baselines, with high user satisfaction, fast preference convergence, and strong safety guarantees, with the system itself consuming only 0.5% of daily battery capacity.

Problem

• mobile power management
• battery life
• user preferences
• context-aware policy
• personalized energy saving

Innovation

• LLM agents
• personalized power management
• semantic-aware policy generation
• constraint verification
• implicit feedback learning