mlsanityData to 14 Oct 2026

From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks

arXiv 2609.30887 ↗First posted 25 Sep 2026cs.AIcited by 0

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

Abstract (arXiv)

Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 47 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

28 of 47 references.

Closest ancestors · 23

Same direction, newest first

  1. 2026UI-Venus-2 Technical Report27 Aug
  2. 2026Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents30 Jul
  3. 2026Xiaomi-GUI-0 Technical Report30 Jun
  4. 2026PhoneBuddy: Training Open Models for Agentic Phone Use22 Jun
  5. 2026MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization18 Jun
  6. 2026AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications26 May
  7. 2026ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents12 May
  8. 2026Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents15 Feb
  9. 2026UI-Venus-1.5 Technical Report9 Feb
  10. 2025MAI-UI Technical Report: Real-World Centric Foundation GUI Agents26 Dec
  11. 2025MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments22 Dec
  12. 2025Step-GUI Technical Report17 Dec
11 more
  1. 2025UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action20 Oct
  2. 2025MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents8 Sep
  3. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning2 Sep
  4. 2025AppAgentX: Evolving GUI Agents as Proficient Smartphone Users4 Mar
  5. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agents21 Jan
  6. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks20 Jan
  7. 2024DroidCall: A Dataset for LLM-powered Android Intent Invocation30 Nov
  8. 2024AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents31 Oct
  9. 2024AutoGLM: Autonomous Foundation Agents for GUIs28 Oct
  10. 2024Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception29 Jan
  11. 2023AppAgent: Multimodal Agents as Smartphone Users21 Dec

Other references · 5

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2026Odysseys: Benchmarking Web Agents on Realistic Long Horizon Taskscited by 21
  3. 2025From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agentscited by 10
  4. 2024Enhancing GUI Exploration Coverage of Android Apps with Deep Link-Integrated Monkeycited by 1
  5. 2026KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skillcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
  2. 2024GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
  3. 2026AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents
  4. 2026APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents
  5. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
  6. 2026VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics
  7. 2026SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis
  8. 2024MobileViews: A Million-scale and Diverse Mobile GUI Dataset