English
Related papers

Related papers: Evaluating Frontier Models for Stealth and Situati…

200 papers

As large language models (LLMs) have demonstrated strong reasoning abilities in structured tasks (e.g., coding and mathematics), we explore whether these abilities extend to strategic multi-agent environments. We investigate strategic…

General Economics · Economics 2025-10-23 Gavin Kader , Dongwoo Lee

This position paper argues for two claims regarding AI testing and evaluation. First, to remain informative about deployment behaviour, evaluations need account for the possibility that AI systems understand their circumstances and reason…

Computer Science and Game Theory · Computer Science 2025-08-22 Vojtech Kovarik , Eric Olav Chen , Sami Petersen , Alexis Ghersengorin , Vincent Conitzer

Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, is widely considered among the most dangerous emergent…

Artificial Intelligence · Computer Science 2026-03-11 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research…

Machine Learning · Computer Science 2026-05-29 Victoria Krakovna , David Lindner , Lewis Ho , Sebastian Farquhar , Rohin Shah

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the…

Artificial Intelligence · Computer Science 2026-03-16 Yihe Fan , Wenqi Zhang , Xudong Pan , Min Yang

We aim to better understand the emergence of `situational awareness' in large language models (LLMs). A model is situationally aware if it's aware that it's a model and can recognize whether it's currently in testing or deployment. Today's…

Computation and Language · Computer Science 2023-09-06 Lukas Berglund , Asa Cooper Stickland , Mikita Balesni , Max Kaufmann , Meg Tong , Tomasz Korbak , Daniel Kokotajlo , Owain Evans

An AI control protocol is a plan for usefully deploying AI systems that aims to prevent an AI from intentionally causing some unacceptable outcome. This paper investigates how well AI systems can generate and act on their own strategies for…

Machine Learning · Computer Science 2025-04-07 Alex Mallen , Charlie Griffin , Misha Wagner , Alessandro Abate , Buck Shlegeris

Recent advances in AI reasoning models provide unprecedented transparency into their decision-making processes, transforming them from traditional black-box systems into models that articulate step-by-step chains of thought rather than…

Software Engineering · Computer Science 2025-03-04 Christoph Treude , Raula Gaikovina Kula

Frontier AI models demonstrate formidable breadth of knowledge. But how close are they to true human -- or superhuman -- expertise? Genuine experts can tackle the hardest problems and push the boundaries of scientific understanding. To…

This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus…

Computers and Society · Computer Science 2025-10-13 Matteo Pistillo , Charlotte Stix

With the increasing integration of frontier large language models (LLMs) into society and the economy, decisions related to their training, deployment, and use have far-reaching implications. These decisions should not be left solely in the…

Can AI reason about a war before its trajectory becomes historically obvious? Analyzing this capability is difficult because retrospective geopolitical prediction is heavily confounded by training-data leakage. We address this challenge…

Artificial Intelligence · Computer Science 2026-03-18 Ming Li , Xirui Li , Tianyi Zhou

Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a possible public release. For example, Anthropic recently developed a new class of model…

Computers and Society · Computer Science 2026-04-30 Oscar Delaney , Sambhav Maheshwari , Joe O'Brien , Theo Bearman , Oliver Guest

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

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Artificial Intelligence · Computer Science 2026-05-07 Xunguang Wang , Yuguang Zhou , Qingyue Wang , Zongjie Li , Ruixuan Huang , Zhenlan Ji , Pingchuan Ma , Shuai Wang

All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…

Computers and Society · Computer Science 2025-06-03 Simon Mylius

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Artificial Intelligence · Computer Science 2025-03-18 Bowen Baker , Joost Huizinga , Leo Gao , Zehao Dou , Melody Y. Guan , Aleksander Madry , Wojciech Zaremba , Jakub Pachocki , David Farhi

Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…

Computers and Society · Computer Science 2025-03-10 Benjamin Hilton , Marie Davidsen Buhl , Tomek Korbak , Geoffrey Irving