# AppVLM: A Lightweight Vision Language Model for Online App Control

arXiv: https://arxiv.org/abs/2502.06395 · HTML: https://mlsanity.com/paper/2502.06395/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [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)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration](https://mlsanity.com/paper/2406.01014/) (2024)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [AndroidEnv: A Reinforcement Learning Platform for Android](https://mlsanity.com/paper/2105.13231/) (2021)
- [SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation](https://mlsanity.com/paper/2410.15164/) (2024)
- [DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents](https://mlsanity.com/paper/2410.14803/) (2024)
- [InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://mlsanity.com/paper/2501.04575/) (2025)
- [Vision-Language Models as a Source of Rewards](https://mlsanity.com/paper/2312.09187/) (2023)
- [Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation](https://mlsanity.com/paper/2312.03003/) (2023)
- [OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning](https://mlsanity.com/paper/2410.18963/) (2024)
- [Ponder & Press: Advancing Visual GUI Agent towards General Computer Control](https://mlsanity.com/paper/2412.01268/) (2024)
- [Lightweight Neural App Control](https://mlsanity.com/paper/2410.17883/) (2024)

## Built on by (most cited first, 15 of 15)

- [AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.01391/) (2025)
- [LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects](https://mlsanity.com/paper/2504.19838/) (2025)
- [A Subgoal-driven Framework for Improving Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.19685/) (2026)
- [MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation](https://mlsanity.com/paper/2507.16853/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Generalization in Online Reinforcement Learning for Mobile Agents](https://mlsanity.com/paper/2603.07432/) (2026)
- [FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data](https://mlsanity.com/paper/2503.05143/) (2025)
- [Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance](https://mlsanity.com/paper/2508.01057/) (2025)
- [Attention Guided Alignment in Efficient Vision-Language Models](https://mlsanity.com/paper/2511.17793/) (2025)
- [A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistants](https://mlsanity.com/paper/2510.06223/) (2025)
- [CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents](https://mlsanity.com/paper/2606.12666/) (2026)
- [Software Engineering for and with GUI Agent](https://mlsanity.com/paper/2608.09278/) (2026)
- [Clip4Retrofit: Enabling Real-Time Image Labeling on Edge Devices via Cross-Architecture CLIP Distillation](https://mlsanity.com/paper/2505.18039/) (2025)
- [Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control](https://mlsanity.com/paper/2509.01720/) (2025)
- [TVWorld: Foundations for Remote-Control TV Agents](https://mlsanity.com/paper/2601.13142/) (2026)

## Abstract (arXiv)

The utilisation of foundation models as smartphone assistants, termed app agents, is a critical research challenge. These agents aim to execute human instructions on smartphones by interpreting textual instructions and performing actions via the device's interface. While promising, current approaches face significant limitations. Methods that use large proprietary models, such as GPT-4o, are computationally expensive, while those that use smaller fine-tuned models often lack adaptability to out-of-distribution tasks. In this work, we introduce AppVLM, a lightweight Vision-Language Model (VLM). First, we fine-tune it offline on the AndroidControl dataset. Then, we refine its policy by collecting data from the AndroidWorld environment and performing further training iterations. Our results indicate that AppVLM achieves the highest action prediction accuracy in offline evaluation on the AndroidControl dataset, compared to all evaluated baselines, and matches GPT-4o in online task completion success rate in the AndroidWorld environment, while being up to ten times faster. This makes AppVLM a practical and efficient solution for real-world deployment.