arXiv AI By Edwin H. Wintermute, Harmon Bhasin, Christina M. Agapakis, Dianzhuo Wang, Evan Seeyave, Arjun Banerjee, Daniel Fulop, Matthew C. Watson, Adam J. Meyer, Sandrine Boissel, Jens H. Kuhn, Rishi Jain, Noah D. Taylor, Helena Shomar, Patrick M. Boyle, Kenny Workman

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 8

Evaluating calibrated refusal and safe usefulness in dual-use biology settings

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.

By Edwin H. Wintermute, Harmon Bhasin, Christina M. Agapakis, Dianzhuo Wang, Evan Seeyave, Arjun Banerjee, Daniel Fulop, Matthew C. Watson, Adam J. Meyer, Sandrine Boissel, Jens H. Kuhn, Rishi Jain, Noah D. Taylor, Helena Shomar, Patrick M. Boyle, Kenny Workman
arXiv AI
Jun 19

Measuring Biological Capabilities and Risks of AI Agents

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.

By Patricia Paskov, Jeffrey Lee, Kyle Brady, Alyssa Worland