arXiv:2606. 19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks.
arXiv:2606. 11150v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data.
arXiv:2607. 05462v2 Announce Type: replace-cross Abstract: As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse.
arXiv:2607. 05462v1 Announce Type: cross Abstract: As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse.
The article introduces Traceable Trust, a framework designed to guide the transition from AI-generated outputs to laboratory actions in bioscience. It outlines a reviewable process that evaluates evidence, claimed capabilities, delegated agency, action thresholds, override mechanisms, and feedback loops. Three case studies demonstrate how the framework can document trust as AI outputs influence scientific work.
arXiv:2610.19810v1 Announce Type: cross Abstract: Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At...
DRYLAB‑Bench is a new benchmark that measures the biosecurity risk of large language models (LLMs) when they design biological mutations. It presents 30 hazardous mutation‑design scenarios and evaluates LLMs in a multi‑round, tool‑augmented setting, scoring designs against 187,695 empirical wet‑lab measurements using a Biosecurity Risk Score. Initial tests on 15 frontier models show that even without tools, a majority of designs exceed average risk, and tool use further amplifies the threat.
Advanced AI can transform biology and medicine—but also raises biosecurity risks. We’re proactively assessing capabilities and implementing safeguards to prevent misuse.
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation.
arXiv:2606. 12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta.
The paper introduces Traceable Trust, a framework designed to guide the transition from AI-generated outputs to laboratory actions in bioscience. It outlines a reviewable process that evaluates evidence, claimed capabilities, delegated agency, action thresholds, override authority, and feedback mechanisms. Three case studies demonstrate how the framework can document trust as AI outputs influence scientific work.
The paper introduces FUSE, a modular framework that evaluates large language models (LLMs) for dangerous capabilities across three orthogonal pipelines: Knowledge (K), Defense (D), and Harm (H). Using a chemical‑biological module, the authors assess 12 commercial LLMs, revealing divergent profiles among models and families, and showing that newer models increase knowledge while only partially improving defense. The framework’s reliability is supported by high cross‑judge consistency and low inter‑pipeline correlations.