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

arXiv: https://arxiv.org/abs/2511.12254 · HTML: https://mlsanity.com/paper/2511.12254/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs](https://mlsanity.com/paper/2404.05719/) (2024)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [AppAgent v2: Advanced Agent for Flexible Mobile Interactions](https://mlsanity.com/paper/2408.11824/) (2024)
- [Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method](https://mlsanity.com/paper/2412.09082/) (2024)
- [A Survey on (M)LLM-Based GUI Agents](https://mlsanity.com/paper/2504.13865/) (2025)
- [Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation](https://mlsanity.com/paper/2312.03003/) (2023)
- [DroidBot-GPT: GPT-powered UI Automation for Android](https://mlsanity.com/paper/2304.07061/) (2023)
- [AppAgentX: Evolving GUI Agents as Proficient Smartphone Users](https://mlsanity.com/paper/2503.02268/) (2025)
- [GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent](https://mlsanity.com/paper/2505.16827/) (2025)
- [Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination](https://mlsanity.com/paper/2411.12591/) (2024)
- [VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning](https://mlsanity.com/paper/2312.11190/) (2023)
- [Cross-Modal Attention Calibration for LVLM Hallucination Mitigation](https://mlsanity.com/paper/2501.01926/) (2025)
- [Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs](https://mlsanity.com/paper/2404.17833/) (2024)
- [Revealing the Barriers of Language Agents in Planning](https://mlsanity.com/paper/2410.12409/) (2024)
- [CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration](https://mlsanity.com/paper/2406.13381/) (2024)

## Built on by (most cited first, 5 of 5)

- [EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation](https://mlsanity.com/paper/2604.20133/) (2026)
- [Jev-Mobile: Jev as an Executor for Mobile GUI Agents](https://mlsanity.com/paper/2609.30186/) (2026)
- [GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning](https://mlsanity.com/paper/2609.14066/) (2026)
- [AgBench: Agentic AI Benchmarks for Personal AI Devices](https://mlsanity.com/paper/2609.38652/) (2026)
- [Learning Reliable GUI Agents under Imperfect Priors](https://mlsanity.com/paper/2609.39547/) (2026)

## Abstract (arXiv)

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.