English
Related papers

Related papers: Measuring Security Without Fooling Ourselves: Why …

200 papers

We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of reliable ground truth for novel research…

Computers and Society · Computer Science 2026-04-07 Marcin Abram

Artificial Intelligence (AI) benchmarks play a central role in measuring progress in model development and guiding deployment decisions. However, many benchmarks quickly become saturated, meaning that they can no longer differentiate…

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier…

Safety frameworks represent a significant development in AI governance: they are the first type of publicly shared catastrophic risk management framework developed by major AI companies and focus specifically on AI scaling decisions. I…

Computers and Society · Computer Science 2024-10-02 Atoosa Kasirzadeh

Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run…

Artificial Intelligence · Computer Science 2026-05-12 Shanshan Gao , Liyi Zhou

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

Web agents have shown great promise in performing many tasks on ecommerce website. To assess their capabilities, several benchmarks have been introduced. However, current benchmarks in the e-commerce domain face two major problems. First,…

Computation and Language · Computer Science 2026-04-22 Xianren Zhang , Shreyas Prasad , Di Wang , Qiuhai Zeng , Suhang Wang , Wenbo Yan , Mat Hans

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 adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias,…

Artificial Intelligence · Computer Science 2025-06-23 Lina Berrayana , Sean Rooney , Luis Garcés-Erice , Ioana Giurgiu

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Artificial Intelligence · Computer Science 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark…

Artificial Intelligence · Computer Science 2026-05-28 Aakash Pant , Kavya Shah , Apoorv Agnihotri , Sneha Nikam , Prasaanth Balraj , Nakul Jain

We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While…

Artificial Intelligence · Computer Science 2026-01-21 Zeshi Dai , Zimo Peng , Zerui Cheng , Ryan Yihe Li

As frontier artificial intelligence (AI) models rapidly advance, benchmarks are integral to comparing different models and measuring their progress in different task-specific domains. However, there is a lack of guidance on when and how…

Computers and Society · Computer Science 2025-07-10 Ayrton San Joaquin , Rokas Gipiškis , Leon Staufer , Ariel Gil

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…

Artificial Intelligence · Computer Science 2025-07-01 Christoph Schnabl , Daniel Hugenroth , Bill Marino , Alastair R. Beresford

Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human…

Computation and Language · Computer Science 2026-05-27 Junlin Wang , Federico Bianchi , Shang Zhu , Fan Nie , Yongchan Kwon , Bhuwan Dhingra , James Zou

Automated control monitors could play an important role in overseeing highly capable AI agents that we do not fully trust. Prior work has explored control monitoring in simplified settings, but scaling monitoring to real-world deployments…

Cryptography and Security · Computer Science 2025-12-30 David Lindner , Charlie Griffin , Tomek Korbak , Roland S. Zimmermann , Geoffrey Irving , Sebastian Farquhar , Alan Cooney

Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks assess isolated skills rather than integrated performance. We find that pre-trained knowledge of…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they…

Computers and Society · Computer Science 2024-08-06 Gabriel Mukobi