Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent miscoordination) even when local generation appears confident. Existing uncertainty proxies focus on single-shot text generation and therefore miss these trajectory-level breakdown signals. We introduce TRACER, a trajectory-level uncertainty metric for dual-control Tool-Agent-User interaction. TRACER combines content-aware surprisal with situational-awareness signals, semantic and lexical repetition, and tool-grounded coherence gaps, and aggregates them using a tail-focused risk functional with a MAX-composite step risk to surface decisive anomalies. We evaluate TRACER on $τ^2$-bench by predicting task failure and selective task execution. To this end, TRACER improves AUROC by up to 37.1% and AUARC by up to 55% over baselines, enabling earlier and more accurate detection of uncertainty in complex conversational tool-use settings. Our code and benchmark are available at https://github.com/sinatayebati/agent-tracer.
PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI
United Arab Emirates University（阿联酋大学）；Khalifa University（哈利法大学）；Interuniversity Microelectronics Centre (IMEC)（校际微电子中心）；Technology Innovation Institute（技术创新研究所）
Dependency-Aware Reward Shaping for Agentic Reinforcement Learning
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）；University of Rochester（罗切斯特大学）
6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management
Shenzhen Smart City Technology Development Group Company, Ltd.（深圳市智慧城市科技发展集团有限公司）；Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（华南理工大学吴贤铭智能工程学院）；China Unicom Group Co., Ltd.（中国联合网络通信集团有限公司）
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
University of British Columbia（英属哥伦比亚大学）；Johns Hopkins University（约翰·霍普金斯大学）；National University of Singapore（新加坡国立大学）；Columbia University（哥伦比亚大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Style3D（无合适对应中文名）
When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows
Independent Researcher（独立研究者）；National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China（健康医学数据科学国家研究院，厦门大学，厦门，中国）；Yue’erwan Internet Hospital Co., Ltd.（悦尔湾互联网医院有限公司）；School of Biomedical Engineering, Tsinghua University, Beijing, China（生物医学工程学院，清华大学，北京，中国）；National University of Singapore, Singapore（新加坡国立大学）；Yttrium-90 Precision Interventional Radiotherapy Center of Liver Cancer, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China（肝癌钇-90精准介入放射治疗中心，北京清华大学昌平医院，临床医学学院，清华大学，北京，中国）；Hepatobiliary and Pancreatic Centre, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China（肝胆胰中心，北京清华大学昌平医院，临床医学学院，清华大学，北京，中国）
UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Peking University（北京大学）；Mininglamp Technology（明略科技）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education（计算力网络与信息安全教育部重点实验室；山东省计算中心（齐鲁工业大学（山东省科学院）））；Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)（计算力互联网与服务计算重点实验室，山东省计算机科学基础研究中心）；Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science
An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
Nanyang Technological University（南洋理工大学）；Singapore Institute of Technology（新加坡理工学院）；Seatrium New Energy Laboratory（Seatrium 新能源实验室）；Ministry of Education (MOE) Tier 1（教育部 Tier 1）；Research Innovation and Enterprise (RIE) 2025 Industry Alignment Fund-Industry Collaboration Projects (IAF-ICP)（研究创新与企业 (RIE) 2025 行业对齐基金-行业合作项目 (IAF-ICP)）
Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback
School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）
