中文
相关论文

相关论文: GUI-GENESIS: Automated Synthesis of Efficient Envi…

200 篇论文

Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting…

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a…

计算与语言 · 计算机科学 2026-01-09 Ziyun Zhang , Zezhou Wang , Xiaoyi Zhang , Zongyu Guo , Jiahao Li , Bin Li , Yan Lu

In this paper, we introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents: verification of trajectory outcome is challenging and high-quality training data are not scalable. These challenges are addressed…

Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains.…

计算与语言 · 计算机科学 2025-05-23 Yuqi Zhou , Sunhao Dai , Shuai Wang , Kaiwen Zhou , Qinglin Jia , Jun Xu

Autonomous agents for long-sequence Graphical User Interface tasks are hindered by sparse rewards and the intractable credit assignment problem. To address these challenges, we introduce GUI-Shepherd, a Process Reward Model that provides…

Despite the rapid progress of multimodal large language models in building Graphical User Interface (GUI) agents, their real-world task completion is fundamentally bottlenecked by a lack of world knowledge about GUI operations. Existing…

计算与语言 · 计算机科学 2026-05-28 Zheng Wu , Chengcheng Han , Zhengxi Lu , Tianjie Ju , Yanyu Chen , Qi Gu , Xunliang Cai , Zhuosheng Zhang

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to…

人工智能 · 计算机科学 2026-02-02 Linjia Kang , Zhimin Wang , Yongkang Zhang , Duo Wu , Jinghe Wang , Ming Ma , Haopeng Yan , Zhi Wang

Recent advancements in large language models (LLMs) have significantly improved the capabilities of web agents. However, effectively navigating complex and dynamic web environments still requires more advanced trajectory-level planning and…

人工智能 · 计算机科学 2025-07-08 Yifei Gao , Junhong Ye , Jiaqi Wang , Jitao Sang

The emergence of Multimodal Large Language Models (MLLMs) has driven significant advances in Graphical User Interface (GUI) agent capabilities. Nevertheless, existing GUI agent training and inference techniques still suffer from a dilemma…

人工智能 · 计算机科学 2026-04-09 Shuquan Lian , Yuhang Wu , Jia Ma , Yifan Ding , Zihan Song , Bingqi Chen , Xiawu Zheng , Hui Li , Rongrong Ji

We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described…

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

计算与语言 · 计算机科学 2025-03-04 Yiheng Xu , Dunjie Lu , Zhennan Shen , Junli Wang , Zekun Wang , Yuchen Mao , Caiming Xiong , Tao Yu

Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a…

Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been limited to semi-automated environment synthesis or tasks…

Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to improve through interaction, its effectiveness critically…

人工智能 · 计算机科学 2025-12-04 Shinji Mai , Yunpeng Zhai , Ziqian Chen , Cheng Chen , Anni Zou , Shuchang Tao , Zhaoyang Liu , Bolin Ding

Traditional approaches to training agents have generally involved a single, deterministic environment of minimal complexity to solve various tasks such as robot locomotion or computer vision. However, agents trained in static environments…

机器人学 · 计算机科学 2025-10-01 Kevin Godin-Dubois , Karine Miras , Anna V. Kononova

We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the…

机器学习 · 计算机科学 2022-02-08 Fabio Ferreira , Thomas Nierhoff , Andreas Saelinger , Frank Hutter

Graphical User Interface (GUI) Agents, powered by large language and vision-language models, hold promise for enabling end-to-end automation in digital environments. However, their progress is fundamentally constrained by the scarcity of…

机器学习 · 计算机科学 2025-09-22 Musen Lin , Minghao Liu , Taoran Lu , Lichen Yuan , Yiwei Liu , Haonan Xu , Yu Miao , Yuhao Chao , Zhaojian Li

Graphical user interface (GUI) agents are rapidly progressing toward autonomous interaction and reliable task execution across diverse applications. However, two central challenges remain unresolved: automating the evaluation of agent…

Recent advancements in Graphical User Interface (GUI) agents have predominantly focused on training paradigms like supervised fine-tuning (SFT) and reinforcement learning (RL). However, the challenge of high-dynamic GUI environments remains…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Enqi Liu , Liyuan Pan , Zhi Gao , Yan Yang , Chenrui Shi , Yang Liu , Jingrong Wu , Qing Li

World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We…

计算机视觉与模式识别 · 计算机科学 2024-10-21 Naser Kazemi , Nedko Savov , Danda Paudel , Luc Van Gool
‹ 上一页 1 2 3 10 下一页 ›