Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and escalating. Using this framework across five domains of recorded human decisions-demand forecasting, content recommendation, content moderation, loan approval, and autonomous driving-and across multiple model families, we find marked differences in the implicit thresholds models use to trade off these costs. These thresholds vary substantially and are not predicted by architecture or scale, while self-estimates are miscalibrated in model-specific ways. We then test interventions that target this decision process by varying cost ratios, providing accuracy signals, and training models to follow the desired escalation rule. Prompting helps mainly for reasoning models. SFT on chain-of-thought targets yields the most robust policies, which generalize across datasets, cost ratios, prompt framings, and held-out domains. These results suggest that escalation behavior is a model-specific property that should be characterized before deployment, and that robust alignment benefits from training models to reason explicitly about uncertainty and decision costs.
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Beijing Academy of Artificial Intelligence(北京人工智能研究院);The Chinese University of Hong Kong(香港中文大学);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation
Singapore Institute of Manufacturing Technology (SIMTech), A*STAR, Singapore(新加坡制造技术研究所);Advanced Remanufacturing and Technology Centre (ARTC), A*STAR, Singapore(先进再制造与技术中心);School of Mechanical and Aerospace Engineering, Nanyang Technological University(机械与航空航天工程学院)
Towards actionable hypotension prediction -- predicting catecholamine therapy initiation in the intensive care unit
University Clinic of Anesthesiology, Intensive Care Medicine, Emergency Medicine, and Pain Therapy(麻醉学、重症医学、急诊医学和疼痛治疗大学诊所);AI4Health Division(AI4Health部门);Carl von Ossietzky Universität(卡尔·冯·奥西特茨基大学)
New York University Tandon School of Engineering(纽约大学Tandon工程学院);University of California, San Diego(加州大学圣地亚哥分校);Stanford University(斯坦福大学);ServiceNow Research(ServiceNow研究);Mila - Quebec AI Institute(魁北克AI研究院);Université de Montréal(蒙特利尔大学)