Related papers: Making AI Agents Evaluate Misleading Charts withou…
AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…
Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…
Analysts often make visual causal inferences about possible data-generating models. However, visual analytics (VA) software tends to leave these models implicit in the mind of the analyst, which casts doubt on the statistical validity of…
Modern businesses are increasingly challenged by the time and expense required to generate and assess high-quality content. Human writers face time constraints, and extrinsic evaluations can be costly. While Large Language Models (LLMs)…
How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…
Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate all available information. In such settings, we study algorithms that highlight a small…
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…
We introduce and study the problem of detecting whether an agent is updating their prior beliefs given new evidence in an optimal way that is Bayesian, or whether they are biased towards their own prior. In our model, biased agents form…
Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…
The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive…
AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human…
Can AI effectively perform complex econometric analysis traditionally requiring human expertise? This paper evaluates AI agents' capability to master econometrics, focusing on empirical analysis performance. We develop ``MetricsAI'', an…
Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents pursuing unintended or unsafe goals. The…
AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic…
Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models. Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined characteristics to members of certain groups and…
Assessing and understanding intelligent agents is a difficult task for users that lack an AI background. A relatively new area, called "Explainable AI," is emerging to help address this problem, but little is known about how users would…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
The use of algorithmic decision making systems in domains which impact the financial, social, and political well-being of people has created a demand for these decision making systems to be "fair" under some accepted notion of equity. This…
The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's behaviour,…