Related papers: Foundations of a Time-Consistent Counterfactual Ac…
AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an…
AI impact assessments often stress near-term risks because human judgment degrades over longer horizons, exemplifying the Collingridge dilemma: foresight is most needed when knowledge is scarcest. To address long-term systemic risks, we…
Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactual explanations for deep reinforcement learning (RL) agents…
Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these…
The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
Experimental user studies evaluating the effectiveness of different subtypes of post-hoc explanations for black-box models are largely nonexistent. Therefore, the aim of this study was to investigate and evaluate how different types of…
The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the…
We study counterfactual prediction under assignment bias and propose a mathematically grounded, information-theoretic approach that removes treatment-covariate dependence without adversarial training. Starting from a bound that links the…
Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risks in human activity, including the persistent hazard of falls among elderly populations.…
The cost and complexity of financial crime compliance (FCC) continue to rise, often without measurable improvements in effectiveness. While AI offers potential, most solutions remain opaque and poorly aligned with regulatory expectations.…
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI (Cybersecurity AI)'s parallel execution framework, we deployed autonomous agents in 23 Attack/Defense CTF battlegrounds.…
Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…
In this paper we present an algorithm for performing runtime verification of a bounded temporal logic over timed runs. The algorithm consists of three elements. First, the bounded temporal formula to be verified is translated into a monadic…
AI-assisted task delegation is increasingly common, yet human effort in such systems is costly and typically unobserved. Recent work by Bastani and Cachon (2025); Sambasivan et al. (2021) shows that accuracy-based payment schemes suffer…
We develop a general framework for the identification of counterfactual parameters in a class of nonlinear semiparametric panel models with fixed effects and time effects. Our method applies to models for discrete outcomes (e.g., two-way…
Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from…
LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…
Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed…