arXiv cs.AI· Junan Hu, Jian Liu, Jingxiang Lai, Jiarui Hu, Yiwei Sheng, Shuang Chen, Jian Li, Dazhao Du, Song Guo·· 4 小时前AI 评分49
强化学习在 GUI 智能体中的应用综述：迈向数字居民
Reinforcement Learning in GUI Agents: A Survey Toward Digital Inhabitants
AI 导读
arXiv 上一篇发表于 TMLR 的综述首次系统梳理了强化学习（RL）与 GUI 智能体的交叉研究，提出将现有方法分为 Offline RL、Online RL 与 Hybrid Strategies 的分类体系，并分析奖励工程与数据效率。
正文 · 原文
Abstract:Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment, distribution shifts, and safe exploration in irreversible environments, making Reinforcement Learning (RL) a central methodology for advancing automation. In this work, we present the first comprehensive overview of the intersection between RL and GUI agents, and examine how this research direction may evolve toward digital inhabitants. We propose a principled taxonomy that organizes existing methods into Offline RL, Online RL, and Hybrid Strategies, and complement it with analyses of reward engineering, data efficiency, and key technical innovations. Our analysis reveals several emerging trends: the tension between reliability and scalability is motivating the adoption of composite, multi-tier reward architectures; GUI I/O latency bottlenecks are accelerating the shift toward world-model-based training, which can yield substantial performance gains; and the spontaneous emergence of System-2-style deliberation suggests that explicit reasoning supervision may not be necessary when sufficiently rich reward signals are available. We distill these findings into a roadmap covering process rewards, continual RL, cognitive architectures, and safe deployment, aiming to guide the next generation of robust GUI automation and its agent-native infrastructure.
| Comments: | Published in TMLR. Project Page: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2604.27955 [cs.AI] |
| (or arXiv:2604.27955v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2604.27955 arXiv-issued DOI via DataCite |
|
| Journal reference: | Transactions on Machine Learning Research, 2026 |
Submission history
From: Junan Hu [view email]
[v1]
Thu, 30 Apr 2026 14:51:49 UTC (7,378 KB)
[v2]
Wed, 4 Nov 2026 02:44:36 UTC (7,383 KB)
来源：arXiv cs.AI · arxiv.org