ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

• URL: http://arxiv.org/abs/2505.16282v1
• Date: Thu, 22 May 2025 06:24:32 GMT
• Title: ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
• Authors: Fanbin Lu, Zhisheng Zhong, Shu Liu, Chi-Wing Fu, Jiaya Jia,
• Abstract summary: Agentic Replay Policy Optimization improves performance on complex, long-horizon computer tasks.<n>We propose a task selection strategy that filters tasks based on baseline agent performance.<n>Experiments on the OSWorld benchmark demonstrate that ARPO achieves competitive results.
• Score: 88.74638385288773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While recent works have advanced multi-turn reinforcement learning (RL) for reasoning and tool-using capabilities in LLMs, their application to GUI-based agents remains relatively underexplored due to the difficulty of sparse rewards, delayed feedback, and high rollout costs. In this paper, we investigate end-to-end policy optimization for vision-language-based GUI agents with the aim of improving performance on complex, long-horizon computer tasks. We propose Agentic Replay Policy Optimization (ARPO), an end-to-end RL approach that augments Group Relative Policy Optimization (GRPO) with a replay buffer to reuse the successful experience across training iterations. To further stabilize the training process, we propose a task selection strategy that filters tasks based on baseline agent performance, allowing the agent to focus on learning from informative interactions. Additionally, we compare ARPO with offline preference optimization approaches, highlighting the advantages of policy-based methods in GUI environments. Experiments on the OSWorld benchmark demonstrate that ARPO achieves competitive results, establishing a new performance baseline for LLM-based GUI agents trained via reinforcement learning. Our findings underscore the effectiveness of reinforcement learning for training multi-turn, vision-language GUI agents capable of managing complex real-world UI interactions. Codes and models:https://github.com/dvlab-research/ARPO.git.

Related papers

• GUI-ReRank: Enhancing GUI Retrieval with Multi-Modal LLM-based Reranking [55.762798168494726]
  GUI-ReRank is a novel framework that integrates rapid embedding-based constrained retrieval models with highly effective MLLM-based reranking techniques.<n>We evaluated our approach on an established NL-based GUI retrieval benchmark.
  arXiv  Detail & Related papers  (2025-08-05T10:17:38Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization [58.65395773049273]
  Location Preference Optimization (LPO) is a novel approach that leverages locational data to optimize interaction preferences.<n>LPO uses information entropy to predict interaction positions by focusing on zones rich in information.<n>Our code will be made publicly available soon, at https://github.com/AIDC-AI/LPO.
  arXiv  Detail & Related papers  (2025-06-11T03:43:30Z)
• MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability [106.35604230971396]
  Recent advancements in Agent techniques enable Large Language Models (LLMs) to autonomously utilize tools for retrieval, planning, and reasoning.<n>To further enhance the universal search capability of agents, we propose a novel pre-training framework, MaskSearch.<n>In the pre-training stage, we introduce the Retrieval Augmented Mask Prediction (RAMP) task, where the model learns to leverage search tools to fill masked spans.<n>After that, the model is trained on downstream tasks to achieve further improvement.
  arXiv  Detail & Related papers  (2025-05-26T17:58:50Z)
• A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning [13.091740188171915]
  We first formalize GUI agent tasks as Markov Decision Processes and discuss typical execution environments and evaluation metrics.<n>We then review the modular architecture of (M)LLM-based GUI agents, covering Perception, Planning, and Acting modules, and trace their evolution through representative works.<n>Our summary illustrates how recent innovations in multimodal perception, decision reasoning, and adaptive action generation have significantly improved the generalization and robustness of GUI agents in complex real-world environments.
  arXiv  Detail & Related papers  (2025-04-29T06:55:15Z)
• Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation [101.09478572153239]
  We propose an approach that guides VLM agents with process supervision by a reward model during GUI navigation and control at inference time.<n>This guidance allows the VLM agent to optimize actions at each inference step, thereby improving performance in both static and dynamic environments.
  arXiv  Detail & Related papers  (2025-04-22T17:52:42Z)
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents [16.72683291432717]
  name is the first reinforcement learning framework designed to enhance the capabilities of LVLMs in high-level real-world task scenarios.<n>name achieves superior performance using only 0.02% of the data compared to previous state-of-the-art methods like OS-Atlas.
  arXiv  Detail & Related papers  (2025-04-14T17:45:54Z)
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning [31.796328505473305]
  We propose UI-R1, the first framework to explore how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks.<n>Specifically, UI-R1 introduces a novel rule-based action reward, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO)<n>For efficient training, we curate a small yet high-quality dataset of 136 challenging tasks, encompassing five common action types on mobile devices.
  arXiv  Detail & Related papers  (2025-03-27T15:39:30Z)
• API Agents vs. GUI Agents: Divergence and Convergence [37.13923771130588]
  API- and GUI-based large language models (LLMs) interact with graphical user interfaces in a human-like manner.<n>This paper systematically analyzes their divergence and potential convergence.<n>We indicate that continuing innovations in LLM-based automation are poised to blur the lines between API- and GUI-driven agents.
  arXiv  Detail & Related papers  (2025-03-14T04:26:21Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)

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.