Related papers: Large-scale Evaluation of Notebook Checkpointing w…
We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative…
Performance optimization is a critical yet challenging aspect of software development, often requiring a deep understanding of system behavior, algorithmic tradeoffs, and careful code modifications. Although recent advances in AI coding…
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…
Interactive visualization can support fluid exploration but is often limited to predetermined tasks. Scripting can support a vast range of queries but may be more cumbersome for free-form exploration. Embedding interactive visualization in…
Notebooks provide an author-friendly environment for iterative development, modular execution, and easy sharing. Distributed workflows are increasingly being authored and executed in notebooks, yet sharing and reproducing them remains…
AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce…
Background: The increasing adoption of AI assistants in programming has led to numerous studies exploring their benefits. While developers consistently report significant productivity gains from these tools, empirical measurements often…
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…
Organizations have widely deployed generative AI tools, yet productivity gains remain uneven, suggesting that how people use AI matters as much as whether they have access. We conducted a field experiment with 388 employees at a Fortune 500…
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce…
Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-time alignment, which uses extra compute at test time to…
Artificial intelligence offers powerful new tools for scientific discovery, but the interaction paradigms required to effectively harness these systems remain underexplored. In this paper, we present findings from a formative user study…
AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics…
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…
Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…
We introduce xbench, a dynamic, profession-aligned evaluation suite designed to bridge the gap between AI agent capabilities and real-world productivity. While existing benchmarks often focus on isolated technical skills, they may not…
Usability inspection is a well-established technique for identifying interaction issues in software interfaces, thereby contributing to improved product quality. However, it is a costly process that requires time and specialized knowledge…
Generative AI tools such as ChatGPT now provide novice programmers with unprecedented access to instant, personalized support. While this holds clear promise, their influence on students' metacognitive processes remains underexplored.…
What do humans do when confronted with a common challenge: we know where we want to go but we are not yet sure the best way to get there, or even if we can. This is the problem posed to agents during spatial navigation and pathfinding, and…
Design optimizations in human-AI collaboration often focus on cognitive aspects like attention and task load. Drawing on work design literature, we propose that effective human-AI collaboration requires broader consideration of human needs…