Related papers: HCAST: Human-Calibrated Autonomy Software Tasks
As AI systems become increasingly capable and autonomous, domain experts' roles are shifting from performing tasks themselves to overseeing AI-generated outputs. Such oversight is critical, as undetected errors can have serious consequences…
AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic…
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly,…
Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they can extend to extreme…
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is…
To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following…
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…
Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a…
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…
Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI). However, recent studies raised concerns over the state of AI benchmarking, reporting issues such as benchmark overfitting, benchmark saturation and…
AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly…
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks,…
Reliable clinical decision support requires medical AI agents capable of safe, multi-step reasoning over structured electronic health records (EHRs). While large language models (LLMs) show promise in healthcare, existing benchmarks…
Validating scientific hypotheses is a central challenge in biomedical research, and remains difficult for artificial intelligence (AI) agents due to the complexity of real-world data analysis and evidence interpretation. In this work, we…
Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web navigation tasks,…
We interact with computers on an everyday basis, be it in everyday life or work, and many aspects of work can be done entirely with access to a computer and the Internet. At the same time, thanks to improvements in large language models…
We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…
Human oversight requirements are a core component of the European AI Act and in AI governance. In this paper, we highlight key challenges in testing for compliance with these requirements. A central difficulty lies in balancing simple, but…
Effective human-AI collaboration for physical task completion has significant potential in both everyday activities and professional domains. AI agents equipped with informative guidance can enhance human performance, but evaluating such…