mlsanityData to 14 Oct 2026

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation

arXiv 2502.02955 ↗First posted 5 Feb 2025cs.CL cs.AIcited by 13

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

Abstract (arXiv)

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most task-relevant elements at each step, leading to local optimal solutions and ignoring the overall GUI flow. To address this issue, we constructed a training dataset called MobileReach, which breaks the task into page reaching and operation subtasks. Furthermore, we propose ReachAgent, a two-stage framework that focuses on improving its task-completion abilities. It utilizes the page reaching and page operation subtasks, along with reward-based preference GUI flows, to further enhance the agent. Experimental results show that ReachAgent significantly improves the IoU Acc and Text Acc by 7.12% and 7.69% on the step-level and 4.72% and 4.63% on the task-level compared to the SOTA agent. Our data and code will be released upon acceptance.

Key facts. Cited by 13 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 22 of its 32 references that are in the map. First posted on arXiv 5 Feb 2025.

Builds on

22 of 32 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents18 Oct
  2. 2024DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning14 Jun
  3. 2024Android in the Zoo: Chain-of-Action-Thought for GUI Agents5 Mar
  4. 2023AppAgent: Multimodal Agents as Smartphone Users21 Dec
  5. 2023CogAgent: A Visual Language Model for GUI Agents14 Dec
  6. 2023You Only Look at Screens: Multimodal Chain-of-Action Agents20 Sep

Other references · 16

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  6. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  7. 2023Android in the Wild: A Large-Scale Dataset for Android Device Controlcited by 319
  8. 2020Mapping Natural Language Instructions to Mobile UI Action Sequencescited by 181
  9. 2023GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigationcited by 137
  10. 2023RLTF: Reinforcement Learning from Unit Test Feedbackcited by 114
  11. 2024ScreenAI: A Vision-Language Model for UI and Infographics Understandingcited by 98
  12. 2021UIBert: Learning Generic Multimodal Representations for UI Understandingcited by 95
4 more
  1. 2023PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedbackcited by 69
  2. 2022ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshotscited by 66
  3. 2024MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understandingcited by 48
  4. 2024MobileAgent: enhancing mobile control via human-machine interaction and SOP integrationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 2.

13 papers.

Sort:

By area:

  1. 2025LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospectscited by 32
  2. 2025BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanismcited by 25
  3. 2025MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuningcited by 19
  4. 2026Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correctioncited by 14
  5. 2025MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automationcited by 11
  6. 2025History-Aware Reasoning for GUI Agentscited by 11
  7. 2025BIMgent: Towards Autonomous Building Modeling via Computer-use Agentscited by 10
  8. 2025MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learningcited by 9
  9. 2025GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agentscited by 8
  10. 2025AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purificationcited by 6
  11. 2026MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Refluxcited by 5
  12. 2025Towards Pervasive Distributed Agentic Generative AI -- A State of The Artcited by 4
1 more
  1. 2025A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistantscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents
  2. 2024ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents
  3. 2025ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation
  4. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
  5. 2024Foundations and Recent Trends in Multimodal Mobile Agents: A Survey
  6. 2025AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
  7. 2025Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents
  8. 2025ColorAgent: Building A Robust, Personalized, and Interactive OS Agent