CLAIMay 18, 2025

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

arXiv:2505.12299v33 citationsh-index: 10
Originality Incremental advance
AI Analysis

This addresses a bottleneck in mobile GUI automation for users needing reliable agents, though it appears incremental as it builds on the existing CoaT paradigm.

The paper tackles the problem of limited expressiveness and generalization in mobile GUI agents caused by scarce diverse reasoning trajectories, proposing an iterative preference learning approach that achieves state-of-the-art performance on three standard benchmarks with strong out-of-domain generalization.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes