OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
University of Science and Technology of China(中国科学技术大学);Shanghai AI Laboratory(上海人工智能实验室);CUHK MMLab(香港中文大学多模态实验室);The Hong Kong University of Science and Technology(香港科学大学);National University of Singapore(新加坡国立大学)
Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggle to achieve both scalability and performance. To address this, we propose OS-Themis, a scalable and accurate multi-agent critic framework. Unlike a single judge, OS-Themis decomposes trajectories into verifiable milestones to isolate critical evidence for decision making and employs a review mechanism to strictly audit the evidence chain before making the final verdict. To facilitate evaluation, we further introduce OmniGUIRewardBench (OGRBench), a holistic cross-platform benchmark for GUI outcome rewards, where all evaluated models achieve their best performance under OS-Themis. Extensive experiments on AndroidWorld show that OS-Themis yields a 10.3% improvement when used to support online RL training, and a 6.9% gain when used for trajectory validation and filtering in the self-training loop, highlighting its potential to drive agent evolution.
AirDreamer: Generalist Drone Navigation with World Models
Institute for AI Industry Research, Tsinghua University, Beijing, China(人工智能产业研究院,清华大学,北京,中国);Department of Electronic Engineering, Tsinghua University, Beijing, China(电子工程系,清华大学,北京,中国);School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China(遥感与信息工程学院,武汉大学,武汉,中国)
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
Zhejiang University(浙江大学);Dalian University of Technology(大连理工大学);Reallm Labs(Reallm实验室);ByteDance Inc(字节跳动公司);The Hong Kong Polytechnic University(香港理工大学)
From Specialist to Generalist: Unlocking SAM's Learning Potential on Unlabeled Medical Images
Carnegie Mellon University(卡内基梅隆大学);Industrial University of Ho Chi Minh City(胡志明市工业大学);University of North Carolina at Charlotte(北卡罗来纳州夏洛特大学);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校)
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Multimodal Art Projection Research Community(多模态艺术投影研究社区);Beijing University of Posts and Telecommunications(北京邮电大学);HKUST(香港科技大学);University of Waterloo(滑铁卢大学);Vector Institute(矢量研究所)
Virginia Tech(弗吉尼亚理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of California, Berkeley(加州大学伯克利分校)
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences(自动化研究所人工智能与自然语言处理实验室,中国科学院);School of Artificial Intelligence, UCAS(中国科学院大学人工智能学院);Meituan(美团)
Inference-Time Scaling for Generalist Reward Modeling
DeepSeek-AI;Dept. of Computer Sci. & Tech., Tsinghua University(计算机科学与技术系,清华大学);Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学)
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
Key Lab of HCST (PKU), MOE(高可信软件技术教育部重点实验室(北京大学);北京大学计算机学院);School of Computer Science, Peking University(北京通明湖信息技术应用创新中心);Beijing Tongming Lake Information Technology Application Innovation Center(腾讯微信);WeChat, Tencent Inc.(西蒙菲莎大学);Simon Fraser University(德克萨斯大学达拉斯分校);University of Texas at Dallas(复旦大学系统与先进计算研究所);Fudan University Institute of Systems for Advanced Computing(上海开放计算系统研究所);Shanghai Institute of Systems for Open Computing