English
Related papers

Related papers: GUI-Shepherd: Reliable Process Reward and Verifica…

200 papers

Developing autonomous agents that effectively interact with Graphic User Interfaces (GUIs) remains a challenging open problem, especially for small on-device models. In this paper, we present Ferret-UI Lite, a compact, end-to-end GUI agent…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Zhen Yang , Zi-Yi Dou , Di Feng , Forrest Huang , Anh Nguyen , Keen You , Omar Attia , Yuhao Yang , Michael Feng , Haotian Zhang , Ram Ramrakhya , Chao Jia , Jeffrey Nichols , Alexander Toshev , Yinfei Yang , Zhe Gan

Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability,…

Artificial Intelligence · Computer Science 2025-04-16 Wenjia Jiang , Yangyang Zhuang , Chenxi Song , Xu Yang , Joey Tianyi Zhou , Chi Zhang

Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search systems that iteratively interact with external knowledge…

Computation and Language · Computer Science 2026-05-19 Guangzhi Xiong , Qiao Jin , Xiao Wang , Yin Fang , Haolin Liu , Yifan Yang , Fangyuan Chen , Zhixing Song , Dengyu Wang , Minjia Zhang , Zhiyong Lu , Aidong Zhang

Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile…

Robotics · Computer Science 2025-07-24 Ning Li , Xiangmou Qu , Jiamu Zhou , Jun Wang , Muning Wen , Kounianhua Du , Xingyu Lou , Qiuying Peng , Jun Wang , Weinan Zhang

Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other…

Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during traversal are often…

Artificial Intelligence · Computer Science 2020-10-07 Deren Lei , Gangrong Jiang , Xiaotao Gu , Kexuan Sun , Yuning Mao , Xiang Ren

In artificial intelligence, we often specify tasks through a reward function. While this works well in some settings, many tasks are hard to specify this way. In deep reinforcement learning, for example, directly specifying a reward as a…

Machine Learning · Computer Science 2019-08-09 Matthew Rahtz , James Fang , Anca D. Dragan , Dylan Hadfield-Menell

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior…

Building autonomous agents that perceive and operate graphical user interfaces (GUIs) like humans has long been a vision in the field of artificial intelligence. Central to these agents is the capability for GUI interaction, which involves…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Hongxin Li , Jingran Su , Jingfan Chen , Zheng Ju , Yuntao Chen , Qing Li , Zhaoxiang Zhang

Mobile GUI agents show promise in automating tasks but face generalization challenges in diverse real-world scenarios. Traditional approaches using pre-training or fine-tuning with massive datasets struggle with the diversity of mobile…

Human-Computer Interaction · Computer Science 2025-04-21 Guangyi Liu , Pengxiang Zhao , Liang Liu , Zhiming Chen , Yuxiang Chai , Shuai Ren , Hao Wang , Shibo He , Wenchao Meng

Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction. However, current evaluation…

Software Engineering · Computer Science 2026-05-29 Xiaoyi Chen , Yifei Gao , Yang Xu , Xingxing Song , Yi Zhang , Jitao Sang

When applying reinforcement learning (RL) to a new problem, reward engineering is a necessary, but often difficult and error-prone task a system designer has to face. To avoid this step, we propose LR4GPM, a novel (deep) RL method that can…

Machine Learning · Computer Science 2023-03-17 Junqi Qian , Paul Weng , Chenmien Tan

Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online…

Human-Computer Interaction · Computer Science 2026-04-09 Yichen Gong , Zhuohan Cai , Sunhao Dai , Yuqi Zhou , Zhangxuan Gu , Changhua Meng , Shuheng Shen

With the widespread adoption of Graphical User Interface (GUI) agents for automating GUI interaction tasks, substantial research focused on improving GUI perception to ground task instructions into concrete action steps. However, the step…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Xuan Wang , Siyuan Su , Quantong Fu , Yongxiang Hu , Yangfan Zhou

Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving…

Multi-turn tool calling is challenging for Large Language Models (LLMs) because rewards are sparse and exploration is expensive. A common recipe, SFT followed by GRPO, can stall when within-group reward variation is low (e.g., more rollouts…

Artificial Intelligence · Computer Science 2026-02-04 Haitian Zhong , Jixiu Zhai , Lei Song , Jiang Bian , Qiang Liu , Tieniu Tan

Identifying underlying user goals and intents has been recognized as valuable in various personalization-oriented settings, such as personalized agents, improved search responses, advertising, user analytics, and more. In this paper, we…

Computation and Language · Computer Science 2025-03-04 Omri Berkovitch , Sapir Caduri , Noam Kahlon , Anatoly Efros , Avi Caciularu , Ido Dagan

Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a…

Machine Learning · Computer Science 2024-02-20 Archit Sharma , Sedrick Keh , Eric Mitchell , Chelsea Finn , Kushal Arora , Thomas Kollar

Context. Multiple automated techniques have been proposed and developed for mobile application GUI testing aiming to improve effectiveness, efficiency, and practicality. The effectiveness, efficiency, and practicality are 3 fundamental…

Software Engineering · Computer Science 2019-01-01 Yauhen Leanidavich Arnatovich , Lipo Wang

Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, fostering a promising hybrid paradigm for MLLM-based mobile automation. However, systematic evaluation of GUI-shortcut hybrid agents…