# Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

arXiv: https://arxiv.org/abs/2509.26539 · HTML: https://mlsanity.com/paper/2509.26539/

## Key facts

- Cited by 16 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 61 of its 67 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 30 of 61)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)

## Built on by (most cited first, 16 of 16)

- [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2512.22047/) (2025)
- [UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action](https://mlsanity.com/paper/2510.17790/) (2025)
- [GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL](https://mlsanity.com/paper/2602.22190/) (2026)
- [UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents](https://mlsanity.com/paper/2602.05832/) (2026)
- [UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience](https://mlsanity.com/paper/2603.24533/) (2026)
- [Step-level Optimization for Efficient Computer-use Agents](https://mlsanity.com/paper/2604.27151/) (2026)
- [SO-Bench: A Structural Output Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2511.21750/) (2025)
- [POINTS-GUI-G: GUI-Grounding Journey](https://mlsanity.com/paper/2602.06391/) (2026)
- [MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents](https://mlsanity.com/paper/2607.11818/) (2026)
- [One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding](https://mlsanity.com/paper/2606.30084/) (2026)
- [Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents](https://mlsanity.com/paper/2605.28775/) (2026)
- [MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models](https://mlsanity.com/paper/2606.04627/) (2026)
- [VUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUs](https://mlsanity.com/paper/2605.01352/) (2026)
- [MintAct: A Unified Visual Agent for Digital Environments](https://mlsanity.com/paper/2609.22083/) (2026)
- [Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?](https://mlsanity.com/paper/2610.07444/) (2026)
- [PEAM: On-device Communication Agent for Personalized, Efficient and Autonomous Mobile Network Configuration](https://mlsanity.com/paper/2610.14855/) (2026)

## Abstract (arXiv)

Developing autonomous agents that effectively interact with Graphic User Interfaces (GUIs) remains a challenging open problem, especially for small on-device models. In this paper, we present Ferret-UI Lite, a compact, end-to-end GUI agent that operates across diverse platforms, including mobile, web, and desktop. Utilizing techniques optimized for developing small models, we build our 3B Ferret-UI Lite agent through curating a diverse GUI data mixture from real and synthetic sources, strengthening inference-time performance through chain-of-thought reasoning and visual tool-use, and reinforcement learning with designed rewards. Ferret-UI Lite achieves competitive performance with other small-scale GUI agents. In GUI grounding, Ferret-UI Lite attains scores of 91.6%, 53.3%, and 61.2% on the ScreenSpot-V2, ScreenSpot-Pro, and OSWorld-G benchmarks, respectively. For GUI navigation, Ferret-UI Lite achieves success rates of 28.0% on AndroidWorld and 19.8% on OSWorld. We share our methods and lessons learned from developing compact, on-device GUI agents.