# Learn from Move: the Next Step for GUI Agents

arXiv: https://arxiv.org/abs/2610.16720 · HTML: https://mlsanity.com/paper/2610.16720/

## 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 33 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [OpenCUA: Open Foundations for Computer-Use Agents](https://mlsanity.com/paper/2508.09123/) (2025)
- [Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents](https://mlsanity.com/paper/2602.16855/) (2026)
- [UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction](https://mlsanity.com/paper/2503.15661/) (2025)
- [DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression](https://mlsanity.com/paper/2609.19969/) (2026)
- [EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience](https://mlsanity.com/paper/2601.15876/) (2026)
- [OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://mlsanity.com/paper/2606.29537/) (2026)
- [CoAct-1: Computer-using Multi-Agent System with Coding Actions](https://mlsanity.com/paper/2508.03923/) (2025)
- [OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents](https://mlsanity.com/paper/2510.24563/) (2025)
- [Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation](https://mlsanity.com/paper/2509.23866/) (2025)
- [Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents](https://mlsanity.com/paper/2505.24878/) (2025)
- [Qwen-CUA: Native Computer Use for (almost) Everything](https://mlsanity.com/paper/2608.02352/) (2026)
- [ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands](https://mlsanity.com/paper/2512.24965/) (2025)
- [GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents](https://mlsanity.com/paper/2606.24551/) (2026)
- [GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks](https://mlsanity.com/paper/2510.26098/) (2025)
- [Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense](https://mlsanity.com/paper/2602.09012/) (2026)
- [CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training](https://mlsanity.com/paper/2603.23559/) (2026)
- [Benchmarking and Improving GUI Agents in High-Dynamic Environments](https://mlsanity.com/paper/2604.25380/) (2026)
- [EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding](https://mlsanity.com/paper/2607.17050/) (2026)
- [ScreenSearch: Uncertainty-Aware OS Exploration](https://mlsanity.com/paper/2605.16024/) (2026)
- [ChartAct: A Benchmark for Dynamic Chart Understanding](https://mlsanity.com/paper/2605.26994/) (2026)
- [CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception](https://mlsanity.com/paper/2608.08392/) (2026)

## Abstract (arXiv)

Existing benchmarks for GUI agents primarily focus on increasing task difficulty by extending task horizons. Besides, enabling agents to explore unfamiliar environments and successfully complete tasks within them is also a critical yet challenging problem. We introduce LatentGUIWorld, a benchmark of six tasks in three matched pairs organized by the evidence needed for control: I0 uses prior knowledge and available observations, I1 requires interaction that directly reveals hidden semantics, and I2 identifies dynamics from action-response relationships. Frontier models struggle especially on I2 tasks. We introduce MOVE, which separates movement from button events and exposes intermediate visual feedback, together with demonstrations of iterative exploration and control. Ablations show that both action granularity and multi-step demonstrations improve performance. After SFT, LatentLearner-9B achieves 50.0% overall success on LatentGUIWorld, comparable to several frontier models. Joint RL further raises egocentric Drag and Ten-Choice success to 92.0% and 75.3%. Behavioral analysis reveals multi-step exploration. In egocentric Drag, RL increases Pearson correlation between error-normalized commands and ideal gain compensation from 0.610 to 0.803. Together, these behaviors show that models learn to explore through interaction and adapt their control to environment dynamics. The same format improves GUI grounding after RL, reaching 67.37% mean accuracy across five benchmarks versus 66.72% for conventional RL.