Related papers: Behind the Prompt: The Agent-User Problem in Infor…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission…
Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, the defect of recommendation algorithms may put users in very…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the integration of LLMs and AI agents with external information sources and…
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…
The practical utility of agent-based models in decision-making relies on their capacity to accurately replicate populations while seamlessly integrating real-world data streams. Yet, the incorporation of such data poses significant…
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks…
AI systems have long been expected to interact with users, answering questions, generating content, and continuing (social) conversations. Agentic AI, however, breaks from this expectation, as its primary objective is workflow execution on…
Recommender systems often rely on models which are trained to maximize accuracy in predicting user preferences. When the systems are deployed, these models determine the availability of content and information to different users. The gap…
Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively…
There is growing imprecision about what "AI agents" are, what they can do, and how effectively they can be used by their intended users. We pose two key research questions: (i) How does the tech industry conceive and market "AI agents"?…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
Models of economic decision makers often include idealized assumptions, such as rationality, perfect foresight, and access to all relevant pieces of information. These assumptions often assure the models' internal validity, but, at the same…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…
The hidden-action model captures a fundamental problem of principal-agent theory and provides an optimal sharing rule when only the outcome but not the effort can be observed. However, the hidden-action model builds on various explicit and…
A long-standing vision of computing is the personal AI system: one that understands us well enough to address our underlying needs. Today's AI focuses on what users do, ignoring why they might be doing such things in the first place. As a…
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is…