ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation
Qinzhuo Wu , Wei Liu , Jian Luan , Bin Wang
- 🏛 Institutions
- XiaoMi AI Lab
- 📅 Date
- April 30, 2025
- 📑 Publisher
- NAACL 2025 (Poster)
- 💻 Env
- Mobile
- 🔑 Keywords
TLDR
ReachAgent addresses the tendency of mobile agents to optimize for the next local action while ignoring the larger GUI flow. It introduces the MobileReach training dataset, which decomposes tasks into page-reaching and page-operation subtasks, and uses those subtasks together with reward-based preference GUI flows to train a two-stage mobile agent.
Related papers (24)
- BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking MechanismMay 27, 2025 · EMNLP 2025 (Oral)
- MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task AutomationApril 30, 2025 · NAACL 2025 (System Demonstrations)
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration BenchmarkApril 18, 2025 · arXiv
- META-GUI: Towards Multi-modal Conversational Agents on Mobile GUIMay 23, 2022 · EMNLP 2022
- SheetCopilot: Bringing Software Productivity to the Next Level through Large Language ModelsMay 30, 2023 · NeurIPS 2023
- Grounding Open-Domain Instructions to Automate Web Support TasksMarch 30, 2021 · NAACL 2021
- MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent ResearchMay 25, 2026 · arXiv
- ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI AgentsApril 13, 2026 · arXiv
- PSPA-Bench: A Personalized Benchmark for Smartphone GUI AgentMarch 31, 2026 · arXiv
- Video-Based Reward Modeling for Computer-Use AgentsMarch 10, 2026 · arXiv
- SecAgent: Efficient Mobile GUI Agent with Semantic ContextMarch 9, 2026 · arXiv
- Turing Test on Screen: A Benchmark for Mobile GUI Agent HumanizationFebruary 24, 2026 · arXiv
- AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the WildFebruary 12, 2026 · arXiv
- MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic EnvironmentsFebruary 3, 2026 · arXiv
- MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge EvolutionJanuary 27, 2026 · arXiv
- SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe SynthesisJanuary 26, 2026 · arXiv
- SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy TasksJanuary 26, 2026 · ICLR 2026 (Poster)
- GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge GraphJanuary 24, 2026 · Journal of Intelligent Computing and Networking
- GUITester: Enabling GUI Agents for Exploratory Defect DiscoveryJanuary 8, 2026 · arXiv
- MobileWorldBench: Towards Semantic World Modeling For Mobile AgentsDecember 16, 2025 · arXiv
- Surfer 2: The Next Generation of Cross-Platform Computer Use AgentsOctober 22, 2025 · arXiv
- CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMsOctober 17, 2025 · NeurIPS 2025 (Poster)
- NaturalGAIA: Pushing the Frontiers of GUI Agents with a Challenging Benchmark and High-Quality Trajectory DatasetAugust 2, 2025 · arXiv
- FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM AgentsJune 9, 2025 · ICLR 2026 (Poster)