Related papers: Overseeing Agents Without Constant Oversight: Chal…
Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code…
Studies show that interactions with an AI system fosters trust in human users towards AI. An often overlooked element of such interaction dynamics is the (sense of) urgency when the human user is prompted by an AI agent, e.g., for advice or…
As the use of interactive AI systems becomes increasingly prevalent in our daily lives, it is crucial to understand how individuals feel when interacting with such systems. In this work, we investigate the comfort level of individuals when…
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…
We show that the ability to lead groups of humans is predicted by leadership skill with Artificially Intelligent agents. In a large pre-registered lab experiment, human leaders worked with AI agents to solve problems. Their performance on…
The automated analysis of human behaviour provides many opportunities for the creation of interactive systems and the post-experiment investigations for user studies. Commodity depth cameras offer reasonable body tracking accuracy at a low…
Agents for computer use (ACUs) are an emerging class of systems capable of executing complex tasks on digital devices -- such as desktops, mobile phones, and web platforms -- given instructions in natural language. These agents can automate…
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…
AI agents are an exciting new research direction, and agent development is driven by benchmarks. Our analysis of current agent benchmarks and evaluation practices reveals several shortcomings that hinder their usefulness in real-world…
Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often inadvertently omit key information when conveying tasks, which…
AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical for establishing…
Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving from experimental prototypes to enterprise deployments. This transition introduces tensions…
[Context and motivation] Trace matrices are lynch pins for the development of mission- and safety-critical software systems and are useful for all software systems, yet automated methods for recovering trace links are far from perfect. This…
LLM-powered computer-use agents (CUAs) are shifting users from direct manipulation to supervisory coordination. Existing oversight mechanisms, however, have largely been studied as isolated interface features, making broader oversight…
As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly critical to ensure alignment. While numerous scalable oversight…
With the rise of generative AI, industry interest in software agents is growing. Given the stochastic nature of generative AI-based agents, their effective and safe deployment in organizations requires robust governance, which can be…
The proliferation of Large Language Model (LLM)-based Graphical User Interface (GUI) agents in web browsing scenarios present complex unintended consequences (UCs). This paper characterizes three UCs from three perspectives: phenomena,…
This exploratory study examined the consistency of human-AI collaboration by analyzing three extensive "vibe coding" sessions between a human product lead and an AI software engineer. We investigated similarities and differences in team…
Human oversight is currently discussed as a potential safeguard to counter some of the negative aspects of high-risk AI applications. This prompts a critical examination of the role and conditions necessary for what is prominently termed…
Communication between humans and artificial agents is essential for their interaction. This is often inspired by human communication, which uses gestures, facial expressions, gaze direction, and other explicit and implicit means. This work…