Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation

TL;DR

This paper introduces Mobile-Agent-RAG, a hierarchical multi-agent framework that enhances long-horizon mobile automation by integrating dual-level retrieval augmentation, significantly improving success rates and efficiency over existing methods.

Contribution

It proposes a novel hierarchical multi-agent system with dual retrieval augmentation for high-level planning and low-level execution, addressing knowledge reliance issues in mobile agents.

Findings

Improved task completion rate by 11.0%.

Enhanced step efficiency by 10.2%.

Outperforms state-of-the-art baselines.

Abstract

Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on static, internal knowledge within MLLMs, which leads to two critical failure points: 1) strategic hallucinations in high-level planning and 2) operational errors during low-level execution on user interfaces (UI). The core insight of this paper is that high-level planning and low-level UI operations require fundamentally distinct types of knowledge. Planning demands high-level, strategy-oriented experiences, whereas operations necessitate low-level, precise instructions closely tied to specific app UIs. Motivated by these insights, we propose Mobile-Agent-RAG, a novel hierarchical multi-agent framework that innovatively integrates dual-level retrieval augmentation. At the planning stage, we introduce Manager-RAG to reduce strategic hallucinations by retrieving human-validated comprehensive task plans that provide high-level guidance. At the execution stage, we develop Operator-RAG to improve execution accuracy by retrieving the most precise low-level guidance for accurate atomic actions, aligned with the current app and subtask. To accurately deliver these knowledge types, we construct two specialized retrieval-oriented knowledge bases. Furthermore, we introduce Mobile-Eval-RAG, a challenging benchmark for evaluating such agents on realistic multi-app, long-horizon tasks. Extensive experiments demonstrate that Mobile-Agent-RAG significantly outperforms SoTA baselines, improving task completion rate by 11.0% and step efficiency by 10.2%, establishing a robust paradigm for context-aware, reliable multi-agent mobile automation.