English
Related papers

Related papers: Measuring Security Without Fooling Ourselves: Why …

200 papers

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

Computers and Society · Computer Science 2026-02-10 Cheng Yu , Severin Engelmann , Ruoxuan Cao , Dalia Ali , Orestis Papakyriakopoulos

Quantitative Artificial Intelligence (AI) Benchmarks have emerged as fundamental tools for evaluating the performance, capability, and safety of AI models and systems. Currently, they shape the direction of AI development and are playing an…

Artificial Intelligence · Computer Science 2025-05-27 Maria Eriksson , Erasmo Purificato , Arman Noroozian , Joao Vinagre , Guillaume Chaslot , Emilia Gomez , David Fernandez-Llorca

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second,…

AI agents are an exciting new research direction, and agent development is driven by benchmarks. Our analysis of current agent benchmarks and evaluation practices reveals several shortcomings that hinder their usefulness in real-world…

Machine Learning · Computer Science 2024-07-02 Sayash Kapoor , Benedikt Stroebl , Zachary S. Siegel , Nitya Nadgir , Arvind Narayanan

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

AI models are increasingly deployed in live clinical environments where they must perform reliably across complex, high-stakes workflows that standard training and validation datasets were never designed to capture. Evaluating these systems…

Artificial Intelligence · Computer Science 2026-05-12 Prasanna Desikan , Harshit Rajgarhia , Shivali Dalmia , Ananya Mantravadi

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Cryptography and Security · Computer Science 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

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…

The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory frameworks constituted on benchmark performance, leaving them…

Machine Learning · Computer Science 2025-12-16 Gabriel Stanovsky , Renana Keydar , Gadi Perl , Eliya Habba

Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability,…

General Finance · Quantitative Finance 2025-06-03 Zichen Chen , Jiaao Chen , Jianda Chen , Misha Sra

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

Artificial Intelligence · Computer Science 2024-11-21 Anka Reuel , Amelia Hardy , Chandler Smith , Max Lamparth , Malcolm Hardy , Mykel J. Kochenderfer

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

Computers and Society · Computer Science 2026-02-24 Nelu D. Radpour

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

Cryptography and Security · Computer Science 2024-12-19 Yifeng He , Ethan Wang , Yuyang Rong , Zifei Cheng , Hao Chen

An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…

Cryptography and Security · Computer Science 2025-11-26 Zehang Deng , Yongjian Guo , Changzhou Han , Wanlun Ma , Junwu Xiong , Sheng Wen , Yang Xiang

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…

Artificial Intelligence · Computer Science 2026-05-01 Ivan Bercovich

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

Cryptography and Security · Computer Science 2026-02-25 Julia Bazinska , Max Mathys , Francesco Casucci , Mateo Rojas-Carulla , Xander Davies , Alexandra Souly , Niklas Pfister

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…

Artificial Intelligence · Computer Science 2026-05-14 Hao Wang , Hanchen Li , Qiuyang Mang , Alvin Cheung , Koushik Sen , Dawn Song

Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…

Computation and Language · Computer Science 2026-02-23 Ali El Filali , Inès Bedar

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…

Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…

Artificial Intelligence · Computer Science 2025-11-19 Sushant Mehta
‹ Prev 1 2 3 10 Next ›