English
Related papers

Related papers: Evaluating Frontier Models for Stealth and Situati…

200 papers

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Artificial Intelligence · Computer Science 2026-01-15 Logan Ritchie , Sushant Mehta , Nick Heiner , Mason Yu , Edwin Chen

Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including…

Artificial Intelligence · Computer Science 2026-05-06 Jie Zhou , Qin Chen , Liang He

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a central AI control problem. Existing monitors often rely on chain-of-thought access or internal…

Computation and Language · Computer Science 2026-05-29 Aditya Sinha , Akshat Naik , Victor Gillioz , Simon Storf , Kilian Merkelbach , Rich Barton-Cooper , Axel Højmark , Marius Hobbhahn

Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide…

Artificial Intelligence · Computer Science 2025-10-22 Antonio-Gabriel Chacón Menke , Phan Xuan Tan , Eiji Kamioka

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

Artificial Intelligence · Computer Science 2025-11-12 Alejandro R. Jadad

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…

Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during…

Artificial Intelligence · Computer Science 2026-04-21 Jiaxin Fang , Runyuan He , Sahil Bhatia , Neel Gajare , Alvin Cheung

Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from…

Computers and Society · Computer Science 2025-03-11 Deepika Raman , Nada Madkour , Evan R. Murphy , Krystal Jackson , Jessica Newman

The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…

Computers and Society · Computer Science 2025-07-29 Mauricio Baker , Gabriel Kulp , Oliver Marks , Miles Brundage , Lennart Heim

As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and…

Cryptography and Security · Computer Science 2025-06-04 David Piorkowski , Michael Hind , John Richards , Jacquelyn Martino

While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc…

Artificial Intelligence · Computer Science 2025-07-08 Scott Emmons , Erik Jenner , David K. Elson , Rif A. Saurous , Senthooran Rajamanoharan , Heng Chen , Irhum Shafkat , Rohin Shah

Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…

Computers and Society · Computer Science 2025-04-22 Heidy Khlaaf , Sarah Myers West

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos…

Artificial Intelligence · Computer Science 2026-04-28 Robert Kirk , Alexandra Souly , Kai Fronsdal , Abby D'Cruz , Xander Davies

Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios. To close this gap, we introduce CLASH (Character…

Computation and Language · Computer Science 2025-09-29 Ayoung Lee , Ryan Sungmo Kwon , Peter Railton , Lu Wang

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Artificial Intelligence · Computer Science 2025-11-11 Maheep Chaudhary , Ian Su , Nikhil Hooda , Nishith Shankar , Julia Tan , Kevin Zhu , Ryan Lagasse , Vasu Sharma , Ashwinee Panda

AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper…

Computers and Society · Computer Science 2026-05-20 Francesca Gomez , Matthew Ball , Michael Harre , Lydia Preston , Josephine Schwab , Caio Machado

The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this position paper, we argue that frontier AI companies should report…

Computers and Society · Computer Science 2025-03-25 Dillon Bowen , Ann-Kathrin Dombrowski , Adam Gleave , Chris Cundy

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior.…