Related papers: Auditing and Controlling AI Agent Actions in Sprea…
AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current…
This paper studies AI persuasion by distinguishing between two reasons for disagreement: attention differences, where the AI detects features the decision-maker missed, and comprehension differences, where the AI and the decision-maker…
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…
Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent…
The recent surge in AI agents that autonomously communicate, collaborate with humans and use diverse tools has unlocked promising opportunities in various real-world settings. However, a vital aspect remains underexplored: how agents handle…
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the…
Automated decision systems (ADS) have become ubiquitous in many high-stakes domains. Those systems typically involve sophisticated yet opaque artificial intelligence (AI) techniques that seldom allow for full comprehension of their inner…
Human-AI collaboration is typically offered in one of two of user control levels: guidance, where the AI provides suggestions and the human makes the final decision, and delegation, where the AI acts autonomously within user-defined…
The transition from human-centric to agent-centric software development practices is disrupting existing knowledge sharing environments for software developers. Traditional peer-to-peer repositories and developer communities for shared…
AI agents are increasingly expected to operate as digital employees: accessing enterprise data, making decisions, and taking actions autonomously. But agents are simultaneously less predictable than humans -- prone to hallucination,…
High-quality scientific review and perspective papers require substantial time and effort, limiting researchers' ability to synthesize emerging knowledge. While Large Language Models (LLMs) leverage AI Scientists for scientific workflows,…
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…
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…
A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and…
The rapid assimilation of Artificial Intelligence technologies into various facets of society has created a significant educational imperative that current frameworks are failing to effectively address. We are witnessing the rise of a…
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…
The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime guardrails, training-time alignment, and post-hoc auditing…
Evaluating human-AI decision-making systems is an emerging challenge as new ways of combining multiple AI models towards a specific goal are proposed every day. As humans interact with AI in decision-making systems, multiple factors may be…
In the evolving landscape of human-centered AI, fostering a synergistic relationship between humans and AI agents in decision-making processes stands as a paramount challenge. This work considers a problem setup where an intelligent agent…
AI systems increasingly assist human decision making by producing preliminary assessments of complex inputs. However, such AI-generated assessments can often be noisy or systematically biased, raising a central question: how should costly…