Related papers: Calibrating Conservatism for Scalable Oversight
AI agents are rapidly advancing from passive language models to autonomous systems executing complex, multi-step tasks. Yet their overconfidence in failure remains a fundamental barrier to deployment in high-stakes settings. Existing…
The field of Contextual Optimization (CO) integrates machine learning and optimization to solve decision making problems under uncertainty. Recently, a risk sensitive variant of CO, known as Conditional Robust Optimization (CRO), combines…
We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-learning problem. A policy gateway maintains a Gaussian-process…
In this paper, we investigate the framework of Online Convex Optimization (OCO) for online learning. OCO offers a very powerful online learning framework for many applications. In this context, we study a specific framework of OCO called…
We study the problem of resource provisioning under stringent reliability or service level requirements, which arise in applications such as power distribution, emergency response, cloud server provisioning, and regulatory risk management.…
As artificial intelligence (AI) / machine learning (ML) gain widespread adoption, practitioners are increasingly seeking means to quantify and control the risk these systems incur. This challenge is especially salient when such systems have…
Conformal prediction is often calibrated with a single pooled threshold, but this can hide cross-group heterogeneity in score distributions and distort group-wise coverage. We study this phenomenon through the population score distributions…
Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization. However, these estimates can be imperfect if the data violates assumptions made by the model (e.g., Gaussianity).…
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…
Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…
As Artificial Intelligence (AI) systems increasingly influence decision-making across various fields, the need to attribute responsibility for undesirable outcomes has become essential, though complicated by the complex interplay between…
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is…
This paper presents an in-depth survey and performance evaluation of the Cat Swarm Optimization (CSO) Algorithm. CSO is a robust and powerful metaheuristic swarm-based optimization approach that has received very positive feedback since its…
Combinatorial optimization assumes that all parameters of the optimization problem, e.g. the weights in the objective function is fixed. Often, these weights are mere estimates and increasingly machine learning techniques are used to for…
Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge sub-optimally when each agent's individual policy gradient…
LLM-based agents are increasingly deployed for expert decision support, yet human-AI teams in high-stakes settings do not yet reliably outperform the best individual. We argue this complementarity gap reflects a fundamental mismatch:…
While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.…
Autoscaling is a technology that automatically scales resources for applications without human intervention to ensure runtime Quality of Service (QoS) while reducing costs. However, user-facing cloud applications serve dynamic workloads…
Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes…