Bridging the Digital to Physical Divide: Evaluating LLM Agents on Benchtop DNA Acquisition

RAND Corporation eBooks 2026 Book

View at publisher
Authors: Kyle Brady, Jeffrey Lee, Dawid Maciorowski, Alyssa M. Worland, Jordan Despanie, Bria Persaud, Barbara Del Castello, Bradley, Henry Alexander, Grant Ellison, Charles Teague, Gebauer, Sarah L., T. Greg McKelvey
+2 more Steph Guerra, Ella Guest
DOI: 10.7249/rra4591-1
Cited by: 0

Abstract

This report describes eight frontier large language model (LLM) agents on their ability to design DNA segments, interact with a benchtop DNA synthesizer, and generate laboratory protocols. These are dual-use tasks, explored as potential technical bottlenecks to a malicious actor building a viral pathogen that could be weaponized. Performance varied among the models, but all tested LLMs designed biologically coherent DNA segments in some attempts.

Fields of Study & Subjects

Law AI and Intellectual Property Adversarial Robustness in Machine Learning Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
RAND Corporation eBooks
Publication date
1 January 2026
Language
EN
Document type
Book