MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

• URL: http://arxiv.org/abs/2505.12299v3
• Date: Mon, 29 Sep 2025 08:49:00 GMT
• Title: MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
• Authors: Kun Huang, Weikai Xu, Yuxuan Liu, Quandong Wang, Pengzhi Gao, Wei Liu, Jian Luan, Bin Wang, Bo An,
• Abstract summary: Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks.<n>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.
• Score: 45.46445208254837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning [30.44007644340425]
  We introduce PROPA, a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations.<n>Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines.<n>It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art.
  arXiv  Detail & Related papers  (2025-11-13T13:06:12Z)
• Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control [72.43808515668947]
  We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control.<n>Hi-Agent features a high-level reasoning model and a low-level action model that are jointly optimized.<n>Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark.
  arXiv  Detail & Related papers  (2025-10-16T07:38:21Z)
• Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following [10.119219532863767]
  lazy reasoning during the thinking stage is the primary factor contributing to poor instruction adherence.<n>We propose a comprehensive framework designed to enable rigorous reasoning processes involving preview and self-checking.<n>Our Light-IF-32B model surpasses both larger open-source models such as DeepSeek-R1 and closed-source models like Doubao-1.6.
  arXiv  Detail & Related papers  (2025-08-05T07:42:00Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [70.01883340129204]
  Single-Pass.<n>with Reference-Guided Evaluation (SPARE)<n>Novel structured framework that enables single-pass, per-step annotation by aligning each solution step to one or multiple steps in a reference solution, accompanied by explicit reasoning for evaluation.<n>SPARE achieves competitive performance on challenging mathematical datasets while offering 2.6 times greater efficiency, requiring only 38% of the runtime.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning [28.291759852111586]
  We introduce a reinforcement learning (RL) based framework that incorporates three core strategies to improve GUI agent performance.<n>With only 3k training samples, our 7B- parameter model achieves state-of-the-art results among similarly sized models.<n> Notably, it attains 47.3% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2%.
  arXiv  Detail & Related papers  (2025-05-18T11:22:04Z)
• Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training [60.38082979765664]
  CPRec is an All-domain Continual Pre-Training framework for Recommendation.<n>It holistically align LLMs with universal user behaviors through the continual pre-training paradigm.<n>We conduct experiments on five real-world datasets from two distinct platforms.
  arXiv  Detail & Related papers  (2025-04-11T20:01:25Z)
• Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection [71.92083784393418]
  Inference-time methods such as Best-of-N (BON) sampling offer a simple yet effective alternative to improve performance.<n>We propose Iterative Agent Decoding (IAD) which combines iterative refinement with dynamic candidate evaluation and selection guided by a verifier.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark [72.46357004059661]
  We propose Similar, a step-wise Multi-dimensional Generalist Reward Model.<n>It offers fine-grained signals for agent training and can choose better action for inference-time scaling.<n>We introduce the first benchmark in the virtual agent domain for step-wise, multi-dimensional reward model training and evaluation.
  arXiv  Detail & Related papers  (2025-03-24T13:30:47Z)
• UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning [8.095763327154335]
  We present our approach to the PerAnsSumm Shared Task, which involves perspective span identification and perspective-aware summarization.<n>For span identification, we adopt ensemble learning that integrates three transformer models through averaging to exploit individual model strengths.<n>For summarization, we design a suite of Chain-of-Thought (CoT) prompting strategies that incorporate keyphrases and guide information to structure summary generation into manageable steps.
  arXiv  Detail & Related papers  (2025-03-14T06:29:51Z)
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)
• Training-Free Unsupervised Prompt for Vision-Language Models [27.13778811871694]
  We propose Training-Free Unsupervised Prompts (TFUP) to preserve inherent representation capabilities and enhance them with a residual connection to similarity-based prediction probabilities. TFUP achieves surprising performance, even surpassing the training-base method on multiple classification datasets. Our TFUP-T achieves new state-of-the-art classification performance compared to unsupervised and few-shot adaptation approaches on multiple benchmarks.
  arXiv  Detail & Related papers  (2024-04-25T05:07:50Z)
• Break a Lag: Triple Exponential Moving Average for Enhanced Optimization [2.0199251985015434]
  We introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average.<n>FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimize learning efficiency.<n>Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures.
  arXiv  Detail & Related papers  (2023-06-02T10:29:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.