# UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding

arXiv: https://arxiv.org/abs/2507.22025 · HTML: https://mlsanity.com/paper/2507.22025/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [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)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (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)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [On the Effects of Data Scale on UI Control Agents](https://mlsanity.com/paper/2406.03679/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models](https://mlsanity.com/paper/2503.04472/) (2025)
- [Aria-UI: Visual Grounding for GUI Instructions](https://mlsanity.com/paper/2412.16256/) (2024)
- [InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners](https://mlsanity.com/paper/2504.14239/) (2025)
- [Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis](https://mlsanity.com/paper/2505.13227/) (2025)
- [GUI Agents with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2411.04890/) (2024)
- [OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition](https://mlsanity.com/paper/2403.19128/) (2024)
- [GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents](https://mlsanity.com/paper/2505.15810/) (2025)
- [VisRL: Intention-Driven Visual Perception via Reinforced Reasoning](https://mlsanity.com/paper/2503.07523/) (2025)

## Built on by (most cited first, 30 of 33)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [UI-Venus Technical Report: Building High-performance UI Agents with RFT](https://mlsanity.com/paper/2508.10833/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents](https://mlsanity.com/paper/2509.18119/) (2025)
- [InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization](https://mlsanity.com/paper/2508.05731/) (2025)
- [UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning](https://mlsanity.com/paper/2510.20286/) (2025)
- [Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage](https://mlsanity.com/paper/2601.01685/) (2026)
- [WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance](https://mlsanity.com/paper/2511.12997/) (2025)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning](https://mlsanity.com/paper/2509.15738/) (2025)
- [HiconAgent: History Context-aware Policy Optimization for GUI Agents](https://mlsanity.com/paper/2512.01763/) (2025)
- [OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution](https://mlsanity.com/paper/2601.20380/) (2026)
- [NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks](https://mlsanity.com/paper/2508.02046/) (2025)
- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions](https://mlsanity.com/paper/2604.07277/) (2026)
- [SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context](https://mlsanity.com/paper/2604.11716/) (2026)
- [Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution](https://mlsanity.com/paper/2509.21072/) (2025)
- [Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements](https://mlsanity.com/paper/2603.14448/) (2026)
- [CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning](https://mlsanity.com/paper/2512.19554/) (2025)
- [UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization](https://mlsanity.com/paper/2604.13822/) (2026)
- [GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks](https://mlsanity.com/paper/2510.26098/) (2025)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents](https://mlsanity.com/paper/2512.21302/) (2025)
- [Benchmarking and Improving GUI Agents in High-Dynamic Environments](https://mlsanity.com/paper/2604.25380/) (2026)
- [BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents](https://mlsanity.com/paper/2601.21352/) (2026)
- [SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning](https://mlsanity.com/paper/2603.23483/) (2026)
- [Rethinking Agentic Reinforcement Learning In Large Language Models](https://mlsanity.com/paper/2604.27859/) (2026)
- [PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control](https://mlsanity.com/paper/2605.15963/) (2026)
- [GUI-AC: Enhancing Continual Learning in GUI Agents](https://mlsanity.com/paper/2606.10522/) (2026)
- [Software Engineering for and with GUI Agent](https://mlsanity.com/paper/2608.09278/) (2026)

## Abstract (arXiv)

The emergence of Multimodal Large Language Models (MLLMs) has driven significant advances in Graphical User Interface (GUI) agent capabilities. Nevertheless, existing GUI agent training and inference techniques still suffer from a dilemma for reasoning designs, ineffective reward, and visual noise. To address these issues, we introduce UI-AGILE for enhancing GUI agents at both training and inference. For training, we propose a suite of improvements to the Supervised Fine-Tuning (SFT) process: 1) a continuous reward function to incentivize high-precision grounding; 2) a ``Simple Thinking'' reward to balance planning with speed and grounding accuracy; and 3) a cropping-based resampling strategy to mitigate the sparse reward problem and improve learning on complex tasks. For inference, we present decomposed grounding with selection to dramatically improve grounding accuracy on high-resolution displays by breaking the image into smaller, manageable parts. Experiments show that UI-AGILE achieves the state-of-the-art grounding performance on two benchmarks ScreenSpot-Pro and ScreenSpot-v2 while it also exhibits strong general agent capabilities. For instance, using both our training and inference enhancement methods brings 23% grounding accuracy improvement over the best baseline on ScreenSpot-Pro. We provide the code in https://github.com/KDEGroup/UI-AGILE.