Related papers: When Should Users Check? Modeling Confirmation Fre…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation…
Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence…
We consider the problem of sequential evaluation, in which an evaluator observes candidates in a sequence and assigns scores to these candidates in an online, irrevocable fashion. Motivated by the psychology literature that has studied…
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…
In many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure…
Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We recast self-correction as a closed-loop feedback-control…
Process supervision, using a trained verifier to evaluate the intermediate steps generated by a reasoner, has demonstrated significant improvements in multi-step problem solving. In this paper, to avoid the expensive effort of human…
Complementary collaboration between humans and AI is essential for human-AI decision making. One feasible approach to achieving it involves accounting for the calibrated confidence levels of both AI and users. However, this process would…
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Cycle-accurate software simulation of multicores with complex microarchitectures is often excruciatingly slow. People use simplified core models to gain simulation speed. However, a persistent question is to what extent the results derived…
Human-AI collaboration for decision-making strives to achieve team performance that exceeds the performance of humans or AI alone. However, many factors can impact success of Human-AI teams, including a user's domain expertise, mental…
In AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, "human self-confidence calibration". We begin by proposing…
Productive human-AI collaboration requires appropriate reliance, yet contemporary AI systems are often miscalibrated, exhibiting systematic overconfidence or underconfidence. We investigate whether humans can learn to mentally recalibrate…
In a conversation, a helpful assistant must reliably follow user directives, even as they refine, modify, or contradict earlier requests. Yet most instruction-following benchmarks focus on single-turn or short multi-turn scenarios, leaving…
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…
In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI's correctness likelihood…
Multi-stream sequential change detection involves simultaneously monitoring many streams of data and trying to detect when their distributions change, if at all. Here, we theoretically study multiple testing issues that arise from detecting…
Objective: We examine how human operators adjust their trust in automation as a result of their moment-to-moment interaction with automation. Background: Most existing studies measured trust by administering questionnaires at the end of an…