English
Related papers

Related papers: Stochasticity in Agentic Evaluations: Quantifying …

200 papers

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…

Machine Learning · Computer Science 2026-03-26 Bjarni Haukur Bjarnason , André Silva , Martin Monperrus

Reporting test-retest reliability using the intraclass correlation coefficient (ICC) has received increasing attention due to the criticisms of poor transparency and replicability in neuroimaging research, as well as many other biomedical…

Methodology · Statistics 2026-01-07 Yufeng Liu , Xiangfei Hong , Shanbao Tong

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…

Artificial Intelligence · Computer Science 2026-05-12 Harsh Raj , Niranjan Orkat , Suvrorup Mukherjee , Aritra Guha , Cheryl Flynn , Subhabrata Majumdar

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…

Accurately estimating the intra-class correlation coefficient (ICC) is crucial for adequately powering clustered randomized trials (CRTs). Challenges arise due to limited prior data on the specific outcome within the target population,…

Methodology · Statistics 2025-04-23 Chen Yang , Márcio A. Diniz , Deukwoo Kwon , Madhu Mazumdar

A good supervised embedding for a specific machine learning task is only sensitive to changes in the label of interest and is invariant to other confounding factors. We leverage the concept of repeatability from measurement theory to…

Sound · Computer Science 2023-10-27 Jianwei Zhang , Suren Jayasuriya , Visar Berisha

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…

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Artificial Intelligence · Computer Science 2025-03-11 Dany Moshkovich , Hadar Mulian , Sergey Zeltyn , Natti Eder , Inna Skarbovsky , Roy Abitbol

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…

Artificial Intelligence · Computer Science 2026-02-24 Stephan Rabanser , Sayash Kapoor , Peter Kirgis , Kangheng Liu , Saiteja Utpala , Arvind Narayanan

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…

Large Language Model (LLM)-based agentic systems have shown growing promise in tackling complex, multi-step tasks through autonomous planning, reasoning, and interaction with external environments. However, the stochastic nature of LLM…

Human-Computer Interaction · Computer Science 2026-03-31 Shuo Yan , Xiaolin Wen , Shaolun Ruan , Yanjie Zhang , Jiaming Mi , Yushi Sun , Huamin Qu , Rui Sheng

The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional techniques, while cornerstone for software quality…

Software Engineering · Computer Science 2023-10-16 Gang Fan , Xiaoheng Xie , Xunjin Zheng , Yinan Liang , Peng Di

As industry reports claim agentic AI systems deliver double-digit productivity gains and multi-trillion dollar economic potential, the validity of these claims has become critical for investment decisions, regulatory policy, and responsible…

Computers and Society · Computer Science 2025-10-03 Kiana Jafari Meimandi , Gabriela Aránguiz-Dias , Grace Ra Kim , Lana Saadeddin , Allie Griffith , Mykel J. Kochenderfer

The intraclass correlation coefficient (ICC) is a classical index of measurement reliability. With the advent of new and complex types of data for which the ICC is not defined, there is a need for new ways to assess reliability. To meet…

Methodology · Statistics 2020-04-29 Meng Xu , Philip T. Reiss , Ivor Cribben

The rapid development in data collecting devices and computation platforms produces an emerging number of agents, each equipped with a unique data modality over a particular population of subjects. While the predictive performance of an…

Machine Learning · Computer Science 2020-10-22 Jiaying Zhou , Xun Xian , Na Li , Jie Ding

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Computation and Language · Computer Science 2026-05-22 Asaf Yehudai , Lilach Eden , Michal Shmueli-Scheuer

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery. Despite recent improvements…

Artificial Intelligence · Computer Science 2026-02-27 Haotian Zhai , Elias Stengel-Eskin , Pratik Patil , Liu Leqi

Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These…

Large language models display a peculiar form of inconsistency: they "know" the correct answer but fail to act on it. In human philosophy, this tension between global judgment and local impulse is called akrasia, or weakness of will. We…

Artificial Intelligence · Computer Science 2025-12-08 Robert Yang
‹ Prev 1 2 3 10 Next ›