TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
East China Normal University（东华师范大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Key Laboratory of Computer Software Evaluating and Testing（上海计算机软件评测与测试重点实验室）；Huawei Noah’s Ark Lab（华为诺亚实验室）
Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumulation without requiring parameter updates. However, even during benign task evolution, agent safety alignment remains vulnerable, a phenomenon known as Agent Memory Misevolution. To evaluate this phenomenon, we construct the Trust-Memevo benchmark and find that agents exhibit an overall decline in trustworthiness across multiple tasks during benign task evolution. To address this issue, we propose TAME, a trust-aware memory evolution framework in which a shared memory bank is jointly governed by an Executor and an Evaluator. The Executor retrieves and applies transferable experiences to support task solving, while the Evaluator assesses the contribution of each utilized experience to the outcome and produces trust-aware feedback to guide subsequent memory use. This executor-evaluator loop enables memory to be selectively reinforced, cautiously reused, and continuously expanded over time. Experiments show that TAME mitigates memory misevolution while achieving strong task performance. In particular, on the GPT-5.2 AIME benchmark, TAME improves accuracy by 14.6 percentage points over the strongest existing method and maintains competitive trustworthiness.
Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
ELLIS Institute Tübingen & MPI-IS & Tübingen AI Center（图宾根ELLIS研究所及MPI-IS与图宾根人工智能中心）；The Alan Turing Institute（艾伦·图灵研究所）；BIFOLD & Technische Universität Berlin（BIFOLD与柏林技术大学）；Technische Universität Darmstadt（达姆施塔特技术大学）
Benchmarking is Broken -- Don't Let AI be its Own Judge
Princeton University（普林斯顿大学）；CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全中心）；Michigan State University（密歇根州立大学）；Ohio State University（俄亥俄州立大学）；Brown University（布朗大学）；Massachusetts Institute of Technology（麻省理工学院）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Tübingen（图宾根大学）；Old Dominion University（旧 Dominion 大学）；Technical University of Munich（慕尼黑技术大学）；Cornell University（康奈尔大学）；Forest AI（森林AI）
Benchmarking Foundation Models with Multimodal Public Electronic Health Records
Centre for Quantitative Medicine and Duke-NUS AI + Medical Science Initiative, Duke-NUS Medical School（定量医学中心和杜克-国立新加坡大学AI+医学科学计划，杜克-国立新加坡大学医学院）；Graduate School of Engineering, The University of Tokyo（东京大学工程研究生院）；Department of Population Health Sciences, Weill Cornell Medicine（流行病学与公共卫生科学系，韦尔·科恩医学中心）；Department of Surgery, Duke University School of Medicine（外科医学系，杜克大学医学学院）；Centre for Quantitative Medicine, Duke-NUS AI + Medical Science Initiative and Programme in Health Services and Systems Research, Duke-NUS Medical School and NUS Artificial Intelligence Institute, National University of Singapore（定量医学中心和杜克-国立新加坡大学AI+医学科学计划及健康服务与系统研究计划，杜克-国立新加坡大学医学院和新加坡国立大学人工智能研究所）
Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification
Fraunhofer Heinrich-Hertz-Institut（弗劳恩霍夫海因里希-赫兹研究所）；Technische Universität Berlin（柏林技术大学）；The Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所）
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（中国科学院自动化研究所，智能科学与技术学院，北京大学）；CISPA Helmholtz Center for Information Security（信息安全研究所）；School of EECS, Peking University（电子工程学院，北京大学）；Institute for Artificial Intelligence, Peking University（人工智能研究所，北京大学）
Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The University of Hong Kong（香港大学）；The University of Sydney（悉尼大学）
NavTrust: Benchmarking Trustworthiness for Embodied Navigation
Trustworthy Autonomous Systems Laboratory at the University of California, Riverside（加州大学河滨分校可信自主系统实验室）；University of Michigan（密歇根大学）；Workday；University of Southern California（南加州大学）；Texas A&M University（德克萨斯A&M大学）；Lehigh University（莱斯大学）
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows
State Key Laboratory for Turbulence and Complex Systems, School of Mechanics and Engineering Science, Peking University（湍流与复杂系统国家重点实验室，力学与工程科学学院，北京大学）；Gaoling School of Artificial Intelligence, Renmin University of China（Gallagher人工智能学院，中国人民大学）；AI for Science Institute（人工智能科学研究院）；University of Calgary（卡尔加里大学）；Kyoto University（京都大学）；FM Global（FM全球）；LandSpace Technology Corporation Ltd.（陆地方向技术有限公司）；Aero Engine Academy of China（中国航空发动机学院）
Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
Department of Physics, J.K. Institute of Science（J.K.科学研究院物理系）；World Scientific University（世界科学大学）；University of Intelligent Studies（智能研究大学）；East China Normal University（华东师范大学）；Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）；Harbin Institute of Technology（哈尔滨工业大学）
FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；China Economics and Management Academy, Central University of Finance and Economics（中央财经大学中国经济与管理研究院）；Asian Institute of Digital Finance, National University of Singapore（新加坡国立大学亚洲数字金融研究所）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
