# MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

arXiv: https://arxiv.org/abs/2505.12299 · HTML: https://mlsanity.com/paper/2505.12299/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 18 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [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)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [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)
- [Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning](https://mlsanity.com/paper/2405.00451/) (2024)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices](https://mlsanity.com/paper/2406.08451/) (2024)
- [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://mlsanity.com/paper/2309.11436/) (2023)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs](https://mlsanity.com/paper/2404.05719/) (2024)
- [Android in the Zoo: Chain-of-Action-Thought for GUI Agents](https://mlsanity.com/paper/2403.02713/) (2024)
- [Aria-UI: Visual Grounding for GUI Instructions](https://mlsanity.com/paper/2412.16256/) (2024)
- [AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents](https://mlsanity.com/paper/2407.17490/) (2024)
- [AutoGLM: Autonomous Foundation Agents for GUIs](https://mlsanity.com/paper/2411.00820/) (2024)
- [AppAgent v2: Advanced Agent for Flexible Mobile Interactions](https://mlsanity.com/paper/2408.11824/) (2024)
- [DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents](https://mlsanity.com/paper/2410.14803/) (2024)
- [Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents](https://mlsanity.com/paper/2407.00993/) (2024)
- [LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation](https://mlsanity.com/paper/2404.16054/) (2024)
- [MobileFlow: A Multimodal LLM For Mobile GUI Agent](https://mlsanity.com/paper/2407.04346/) (2024)
- [Falcon-UI: Understanding GUI Before Following User Instructions](https://mlsanity.com/paper/2412.09362/) (2024)
- [MobileAgent: enhancing mobile control via human-machine interaction and SOP integration](https://mlsanity.com/paper/2401.04124/) (2024)
- [Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents](https://mlsanity.com/paper/2505.11891/) (2025)
- [ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation](https://mlsanity.com/paper/2502.02955/) (2025)
- [MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users](https://mlsanity.com/paper/2502.02982/) (2025)

## Built on by (most cited first, 9 of 9)

- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization](https://mlsanity.com/paper/2511.13091/) (2025)
- [Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding](https://mlsanity.com/paper/2605.00642/) (2026)
- [How Mobile World Model Guides GUI Agents?](https://mlsanity.com/paper/2605.10347/) (2026)
- [Xiaomi-GUI-0 Technical Report](https://mlsanity.com/paper/2606.31410/) (2026)
- [PhoneBuddy: Training Open Models for Agentic Phone Use](https://mlsanity.com/paper/2606.23049/) (2026)
- [AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents](https://mlsanity.com/paper/2608.05891/) (2026)
- [PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents](https://mlsanity.com/paper/2605.29486/) (2026)
- [BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents](https://mlsanity.com/paper/2609.12394/) (2026)

## Abstract (arXiv)

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.