mlsanityData to 7 Oct 2026

Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration

arXiv 2406.01014 ↗First posted 3 Jun 2024cs.CL cs.CVcited by 187

On the map: LLM agents and tool use → GUI and mobile agents

Abstract (arXiv)

Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as operation assistants. Instead, MLLM-based agents, which enhance capabilities through tool invocation, are gradually being applied to this scenario. However, the two major navigation challenges in mobile device operation tasks, task progress navigation and focus content navigation, are significantly complicated under the single-agent architecture of existing work. This is due to the overly long token sequences and the interleaved text-image data format, which limit performance. To address these navigation challenges effectively, we propose Mobile-Agent-v2, a multi-agent architecture for mobile device operation assistance. The architecture comprises three agents: planning agent, decision agent, and reflection agent. The planning agent generates task progress, making the navigation of history operations more efficient. To retain focus content, we design a memory unit that updates with task progress. Additionally, to correct erroneous operations, the reflection agent observes the outcomes of each operation and handles any mistakes accordingly. Experimental results indicate that Mobile-Agent-v2 achieves over a 30% improvement in task completion compared to the single-agent architecture of Mobile-Agent. The code is open-sourced at https://github.com/X-PLUG/MobileAgent.

Key facts. Cited by 187 papers in the map (data through 7 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 48 of its 55 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

48 of 55 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception29 Jan
  2. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents17 Jan
  3. 2023AppAgent: Multimodal Agents as Smartphone Users21 Dec
  4. 2023CogAgent: A Visual Language Model for GUI Agents14 Dec

Other references · 44

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  9. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  10. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  12. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
32 more
  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  3. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  4. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  5. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  6. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  7. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  8. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  9. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  10. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  11. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  12. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  13. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  14. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 314
  15. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 293
  16. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 254
  17. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  18. 2024mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understandingcited by 220
  19. 2023AutoDroid: LLM-powered Task Automation in Androidcited by 178
  20. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Gamecited by 148
  21. 2024UFO: A UI-Focused Agent for Windows OS Interactioncited by 147
  22. 2023GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigationcited by 137
  23. 2023Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challengescited by 131
  24. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Modelscited by 99
  25. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  26. 2024Octopus v2: On-device language model for super agentcited by 45
  27. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
  28. 2023mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Modelcited by 31
  29. 2023ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Modelscited by 24
  30. 2024Octopus v4: Graph of language modelscited by 11
  31. 2024Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agentcited by 7
  32. 2024Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answeringcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 18; 2025: 102; 2026: 67.

187 papers.

Sort:

By area:

  1. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
  2. 2024mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Modelscited by 285
  3. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 244
  4. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  5. 2024GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devicescited by 190
  6. 2025Mobile-Agent-v3: Fundamental Agents for GUI Automationcited by 183
  7. 2025UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learningcited by 166
  8. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  9. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
  10. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  11. 2024GUI Agents with Foundation Models: A Comprehensive Surveycited by 110
  12. 2025UI-Venus Technical Report: Building High-performance UI Agents with RFTcited by 90
38 more
  1. 2024SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluationcited by 79
  2. 2025Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learningcited by 79
  3. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  4. 2024o1-Coder: an o1 Replication for Codingcited by 77
  5. 2026Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agentscited by 72
  6. 2024DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agentscited by 68
  7. 2025A Survey on (M)LLM-Based GUI Agentscited by 61
  8. 2025GUI-G2: Gaussian Reward Modeling for GUI Groundingcited by 60
  9. 2025Training-Free Group Relative Policy Optimizationcited by 53
  10. 2024Ferret-UI 2: Mastering Universal User Interface Understanding Across Platformscited by 51
  11. 2025AppAgentX: Evolving GUI Agents as Proficient Smartphone Userscited by 44
  12. 2026Code as Agent Harnesscited by 40
  13. 2026UI-Venus-1.5 Technical Reportcited by 39
  14. 2026Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Taskscited by 37
  15. 2025GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agentcited by 35
  16. 2025ViMo: A Generative Visual GUI World Model for App Agentscited by 33
  17. 2025UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agentscited by 33
  18. 2024Foundations and Recent Trends in Multimodal Mobile Agents: A Surveycited by 31
  19. 2024AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generationcited by 31
  20. 2025LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospectscited by 31
  21. 2025UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interfacecited by 27
  22. 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automationcited by 27
  23. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  24. 2025OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agentscited by 25
  25. 2025OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agentscited by 25
  26. 2025Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systemscited by 23
  27. 2025MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environmentscited by 23
  28. 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learningcited by 23
  29. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 22
  30. 2025GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behaviorcited by 22
  31. 2025Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attackscited by 21
  32. 2025Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inferencecited by 20
  33. 2025VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verificationcited by 20
  34. 2024Infogent: An Agent-Based Framework for Web Information Aggregationcited by 19
  35. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  36. 2025SpiritSight Agent: Advanced GUI Agent with One Lookcited by 18
  37. 2025Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skillscited by 18
  38. 2025MobileWorldBench: Towards Semantic World Modeling For Mobile Agentscited by 18

50 most cited of 187 All 187 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices
  2. 2025ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation
  3. 2025Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation
  4. 2025AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
  5. 2025Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
  6. 2026PalmClaw: A Native On-Device Agent Framework for Mobile Phones
  7. 2026OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
  8. 2025Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment