CORTEXA
← Browse
arxivcs.AI2026-07-17

Harmonizing AI Safety Thresholds

Wilber Sean Anterola, Matthew Ball, Luis F. Lafuerza, Markov Grey

Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies. Moreover, without common minimum thresholds, risk mitigation may be inconsistent, creating a potential race to the bottom in safety standards. We develop a methodology for deriving harmonized thresholds across three risk domains. For misuse risks (cyber and biological), we take expected harm as the key primitive and use an explicit risk-modeling approach that accounts for risk channels and model release conditions. For automated AI R&D, we base our proposed threshold on the observed rate of AI progress rather than expected harm. Our analysis expands upon prior work and highlights existing empirical gaps and limitations.

View free PDFSource page

Related papers

arxivcs.AI2026-07-31

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

Minghui Pan, Jiayuxuan Yang, Yuanyuan Yuan, Yu Jiang, Zhenpeng Chen

AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions. Yet LLMs often become substantially less safe when deployed as agents, and the source of this degradation r…

View free PDFSource page
arxivcs.CVcs.AI2026-07-23

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation

Dongbin Na

A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up with the stream and stop a harmful reply before a user reads it. Recent vision-language guardrails instead generate a chain of thou…

View free PDFSource page
arxivcs.AIcs.MA2026-07-23

SafeStep: AI-powered Travel Assistance for Elderly People with Frailty or Dementia

Elderly People with Frailty or Dementia Azul Debenedetti, David Gamez, Franco Such, Nik Kairinos

More than a million people in the UK suffer from frailty or dementia, which severely compromise their ability to travel in urban environments. This paper presents SafeStep, an AI-driven travel system that assists elderly users with their journeys. At the core of SafeStep is a nov…

View free PDFSource page
arxivcs.AI2026-07-24Cited by 2

Explainable Reinforcement Learning for assisting Air Traffic Controllers

Anduel Mehmeti, Gabriella Gigante, Salvatore Venticinque

To effectively integrate AI into high-stakes, critical environments such as healthcare, autonomous driving, and aviation--and to advance toward higher levels of automation and seamless human-AI collaboration--building trust in AI-driven solutions is essential. Trust, in turn, is…

View free PDFSource page
arxivcs.AIcs.MAcs.SE2026-07-31

Beyond Component Testing: Validating Agentic AI Systems

Fabio Orazio Mirto, Luca D'Agati, Giuseppe Tricomi, Stefano Silvestri, Francesco Longo, Antonio Puliafito, et al.

Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice beyond component testing and one-shot input--output evaluation, because acceptable system behavior now depends…

View free PDFSource page
arxivcs.AIcs.CL2026-07-23

Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

Mack Nixon, Liam Wright, Yevgeniya Kovalchuk, Alison Fang-Wei Wu, Martin Danka, Andy Boyd, et al.

Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their adoption in research using personal data is constrained by governance requirements that typically prohibit data transmission to…

View free PDFSource page